Clay

Add data points to companies in an existing search. Supports enriching ALL companies or specific companies via entityIds.

Quick Reference

• This tool: Enrich COMPANIES with funding, tech stack, headcount, etc.
• add-contact-data-points: Enrich CONTACTS with emails, work history, etc.
• Requires a taskId from a previous search-* tool call
• Use entityIds to enrich specific companies — do NOT create a new search to enrich one company from an existing search
• ANY research question about companies = call this tool with a Custom data point

IMPORTANT: When to Call This Tool

Check before enriching: If the user asks about a specific company's data (e.g. "what's their tech stack?"), call get-task-context FIRST — the user may have already enriched it through the widget. Only call this tool if get-task-context shows the enrichment hasn't been run.

Call this tool whenever the user asks to FETCH or ADD new information about companies, including:

• Standard data points (tech stack, funding, headcount, etc.)
• Any open-ended research question — use Custom type for these

Do NOT try to answer company research questions from your own knowledge. ALWAYS call this tool or get-task-context to fetch the data.

Examples that MUST trigger this tool:

• "What's their tech stack?" → Standard type
• "Find recent product announcements" → Custom type
• "Get me their latest news" → Custom type
• "What's their revenue model?" → Custom type
• "Find their competitors" → Custom type
• "Any recent acquisitions?" → Custom type

Parameters

taskId (required)

The task ID returned from search-contacts or search-contacts-by-name.

• Do NOT fabricate a taskId—use the one from the prior search
• If no search exists yet, prompt the user to search first

dataPoints (required)

Array of data points to add.

• Standard: { type: "<DataPointType>" }
• Custom: { type: "Custom", customDataPoint: "<brief description>" }

Available standard types: Headcount Growth, Recent News, Investors, Company Competitors, Company Customers, Tech Stack, Website Traffic, Open Jobs, Revenue Model, Annual Revenue, Latest Funding

Custom type: Use for ANY research question not covered by standard types. Examples:

• "recent product announcements" → { type: "Custom", customDataPoint: "recent product announcements" }
• "B2B vs B2C classification" → { type: "Custom", customDataPoint: "B2B vs B2C classification" }
• "company founders" → { type: "Custom", customDataPoint: "company founders" }

entityIds (optional)

Array of entityIds to enrich. When omitted, enriches all companies in the search.

• Use the entityId values from the company data returned by a previous search tool call
• Useful when the user wants to enrich specific companies

Examples

| User request | dataPoints | |--------------|------------| | "What's their tech stack?" | [{ type: "Tech Stack" }] | | "Get funding info and headcount" | [{ type: "Latest Funding" }, { type: "Headcount" }] | | "Find recent product announcements" | [{ type: "Custom", customDataPoint: "recent product announcements" }] | | "Are they B2B or B2C?" | [{ type: "Custom", customDataPoint: "B2B vs B2C classification" }] | | "What's in the news about them?" | [{ type: "Custom", customDataPoint: "recent news and headlines" }] |

Response Behavior

• Confirm briefly: "Fetching [data point] for [company/companies]."
• For single-company requests, name the company instead of saying "all companies."

Clay may render results in a widget in hosts that support MCP Apps, such as ChatGPT, claude.ai, and Cursor. Other terminal/coding-agent hosts such as Codex, Claude Code, Windsurf, and CLI environments do not show the widget. If you are unsure whether the widget is visible, assume it is not visible.

• If a widget is visible, avoid repeating the full widget contents unless the user asks for full contents; then call get-task-context with the taskId and answer inline.
• In terminal/coding-agent environments, when no widget is visible, or when the user asks for actual values/results, call get-task-context with the taskId and answer inline.
• NEVER tell the user that data was not found, not returned, or unavailable without first calling get-task-context. The initial search/tool response only includes base fields — enrichment results (emails, X/Twitter profiles, work history, custom data points, etc.) are only available via get-task-context.
• When the user asks about a specific value (e.g. "what's Patrick's email?", "what X profiles did you get?"), call get-task-context FIRST to check if the data has already been enriched — the user may have triggered enrichments through the widget. Only call add-contact-data-points / add-company-data-points if get-task-context shows the enrichment hasn't been run yet.
• Use get-task-context to poll until async results complete; if values are still in-progress, wait and retry rather than answering with missing values.
• If get-task-context is not available, fall back to get-task.

Add data points to contacts in an existing search. Supports enriching ALL contacts or specific contacts via entityIds.

Quick Reference

• This tool: Enrich CONTACTS with emails, work history, etc.
• add-company-data-points: Enrich COMPANIES with funding, tech stack, headcount, etc.
• Requires a taskId from a previous search-* tool call
• Use entityIds to enrich specific contacts — do NOT create a new search to enrich one person from an existing search
• ANY research question about contacts = call this tool with a Custom data point

IMPORTANT: When to Call This Tool

Check before enriching: If the user asks about a specific contact's data (e.g. "what's Patrick's email?"), call get-task-context FIRST — the user may have already enriched it through the widget. Only call this tool if get-task-context shows the enrichment hasn't been run.

Call this tool whenever the user asks to FETCH or ADD new information about contacts, including:

• Standard data points (email, work history, etc.)
• Any open-ended research question — use Custom type for these

Do NOT try to answer contact research questions from your own knowledge. ALWAYS call this tool or get-task-context to fetch the data.

Examples that MUST trigger this tool:

• "Get their emails" → Standard type
• "Find their recent publications" → Custom type
• "What have they posted on LinkedIn?" → Custom type
• "Summarize their career trajectory" → Custom type
• "Any recent job changes?" → Custom type
• "Score them against my ICP" → Custom type

Parameters

taskId (required)

The task ID returned from search-contacts or search-contacts-by-name.

• Do NOT fabricate a taskId—use the one from the prior search
• If no search exists yet, prompt the user to search first

dataPoints (required)

Array of data points to add.

• Standard: { type: "<DataPointType>" }
• Custom: { type: "Custom", customDataPoint: "<brief description>" }

Available standard types: Email, Summarize Work History, Find Thought Leadership

Custom type: Use for ANY research question not covered by standard types. Examples:

• "recent publications" → { type: "Custom", customDataPoint: "recent publications" }
• "LinkedIn activity" → { type: "Custom", customDataPoint: "recent LinkedIn posts" }
• "ICP fit score" → { type: "Custom", customDataPoint: "ICP fit score based on seniority and tenure" }

entityIds (optional)

Array of entityIds to enrich. When omitted, enriches all contacts in the search.

• Use the entityId values from the contact data returned by a previous search tool call
• Useful when the user wants to enrich specific contacts (e.g., "get John's email")

Examples

| User request | dataPoints | |--------------|------------| | "Get their emails" | [{ type: "Email" }] | | "Add work history" | [{ type: "Summarize Work History" }] | | "Find their recent publications" | [{ type: "Custom", customDataPoint: "recent publications" }] | | "What's their LinkedIn activity?" | [{ type: "Custom", customDataPoint: "recent LinkedIn posts" }] | | "Score them for senior leaders in NYC" | [{ type: "Custom", customDataPoint: "ICP fit: senior leader in NYC" }] | | "Get John's email" (single contact) | [{ type: "Email" }] + entityIds: ["<john's entityId>"] |

Response Behavior

• Confirm briefly: "Fetching [data point] for all contacts."
• For single-contact requests, name the contact instead of saying "all contacts."

Clay may render results in a widget in hosts that support MCP Apps, such as ChatGPT, claude.ai, and Cursor. Other terminal/coding-agent hosts such as Codex, Claude Code, Windsurf, and CLI environments do not show the widget. If you are unsure whether the widget is visible, assume it is not visible.

• If a widget is visible, avoid repeating the full widget contents unless the user asks for full contents; then call get-task-context with the taskId and answer inline.
• In terminal/coding-agent environments, when no widget is visible, or when the user asks for actual values/results, call get-task-context with the taskId and answer inline.
• NEVER tell the user that data was not found, not returned, or unavailable without first calling get-task-context. The initial search/tool response only includes base fields — enrichment results (emails, X/Twitter profiles, work history, custom data points, etc.) are only available via get-task-context.
• When the user asks about a specific value (e.g. "what's Patrick's email?", "what X profiles did you get?"), call get-task-context FIRST to check if the data has already been enriched — the user may have triggered enrichments through the widget. Only call add-contact-data-points / add-company-data-points if get-task-context shows the enrichment hasn't been run yet.
• Use get-task-context to poll until async results complete; if values are still in-progress, wait and retry rather than answering with missing values.
• If get-task-context is not available, fall back to get-task.

Ask a natural language question about one or more accounts available in Clay Audiences. Depending on your workspace settings and whether Salesforce owner data is available, this may be limited to accounts you own in Salesforce. An AI agent analyzes account data including contacts, opportunities, Gong calls, and emails to answer your question.

IMPORTANT: Both "accountIds" and "question" parameters are REQUIRED — you must always provide both when calling this tool.

Quick Reference

• This tool: Ask questions or get analysis about specific accounts (e.g., "What's the status of this deal?", "Who are the key stakeholders?")
• query-objects: Call this first to get account entity IDs before calling this tool, unless you already have account IDs. Find and list accessible accounts by natural-language filters.
• find-and-enrich-company: Only for prospecting publicly available company info. Do NOT use find-and-enrich-company when the user is asking about their own accounts or deals; use this tool instead.
• For ambiguous queries (e.g., "Tell me about Acme"), call query-objects first. If the account exists, use this tool. If not, fall back to find-and-enrich-company.

Prerequisites

You need the accountId (numeric) for each account you want to ask about. If you don't have it: 1. Call query-objects to find accounts by name or other natural-language filters. Use onlyMine: true when the user asks about "my" accounts or accounts they personally own; omit it when they ask about accounts in general. 2. Use the returned account entityId values as accountIds

Access to specific accounts depends on your workspace settings. Some workspaces allow questions about any account in the audience, while others restrict questions to accounts you own in Salesforce when Salesforce owner data is available.

Parameters

accountIds (required — MUST be provided)

Array of numeric account IDs from returned account entityId values in the query-objects response. Supports 1-10 accounts.

• For single-account questions: provide one ID (e.g., [12345])
• For multi-account questions (e.g., comparisons): provide multiple IDs (e.g., [12345, 67890]). The tool returns individual analyses for each account — you should synthesize and compare the results yourself.

question (required — MUST be provided)

A natural language question about the account(s). Be specific for best results.

Correct Usage

You MUST always call this tool with BOTH parameters like this: { "accountIds": [12345], "question": "What is the deal status?" }

Examples

| User says | How to handle | |-----------|---------------| | "What's happening with the Acme deal?" | 1. Call query-objects with query: "Acme account" to get the account entityId. 2. Call this tool with that entityId in accountIds and the question. | | "What's happening with my Acme deal?" | 1. Call query-objects with query: "Acme account" and onlyMine: true to get the account entityId. 2. If Clay says owner-scoped filtering is unavailable, explain that Clay can still search audience accounts but cannot determine ownership in this workspace. 3. Otherwise call this tool with that entityId in accountIds and the question. | | "Compare my top two accounts" | 1. Call query-objects with query: "my accounts" and onlyMine: true to find accounts. 2. If owner-scoped filtering is unavailable, explain that Clay can still analyze audience accounts but cannot determine ownership in this workspace. 3. Otherwise call this tool with both entityIds in accountIds and the question. The tool returns individual analyses per account; synthesize and compare the results yourself. | | "Who are the key contacts at account 12345?" | Call this tool directly with accountIds: [12345] and question: "Who are the key contacts?" (ID already known). |

Response Behavior

• Returns a detailed text answer from the AI agent based on each account's data
• The agent analyzes contacts, opportunities, Gong call transcripts, and emails
• For multi-account requests, individual analyses are returned per account — you are responsible for comparing or synthesizing the results
• This tool may take longer than other tools due to the depth of analysis

Find and enrich a single company by domain or LinkedIn URL.

Quick Reference

• This tool: Prospect and research PUBLICLY AVAILABLE company info (e.g., "Tell me about Stripe", "What's OpenAI's funding?"). This is for prospecting external data, NOT for querying the user's own account data.
• find-and-enrich-contacts-at-company: Find TYPES of people (e.g., "engineers at Stripe")
• find-and-enrich-list-of-contacts: Find SPECIFIC named people (e.g., "John Smith at Stripe")
• get-my-accounts + ask-question-about-accounts: Ask about the user's OWN accounts, deals, CRM data, or relationships (e.g., "What's happening with my Acme deal?", "How's our relationship with Stripe?")
• Do NOT use if user wants to find people—use the contact tools instead
• Do NOT use if user is asking about their own accounts, deals, opportunities, or CRM data—use get-my-accounts and ask-question-about-accounts instead
• For ambiguous queries about a company (e.g., "Tell me about Acme"), prefer checking get-my-accounts first. Only use this tool if the account is not found or the user is explicitly prospecting.

Parameters

companyIdentifier (required)

Domain (e.g., "stripe.com") or LinkedIn company URL. Company names alone will fail.

• Convert known companies: "Stripe" → "stripe.com"
• If ambiguous (e.g., "Delta"), ask the user to clarify

companyDataPoints (optional)

Enrich the company when creating a NEW search. For existing searches, use add-company-data-points instead.

⚠️ CRITICAL: NEVER add data points unless the user EXPLICITLY asks for them. Enrichments cost credits. Only include data points when the user's message specifically requests that data.

• "Tell me about Stripe" → NO data points
• "What's Stripe's funding?" → add Latest Funding (user explicitly asked)
• Do NOT add Headcount Growth, Recent News, or any other data point "to be helpful" — only what the user asked for

DataPoint format:

• Standard: { type: "<DataPointType>" }
• Custom: { type: "Custom", customDataPoint: "<brief description>" }

Important: Only include customDataPoint field when type is "Custom"

Available companyDataPoints: Headcount Growth, Recent News, Investors, Company Competitors, Company Customers, Tech Stack, Website Traffic, Open Jobs, Revenue Model, Annual Revenue, Latest Funding

Examples

| User request | Parameters | |--------------|------------| | "Tell me about Stripe" | companyIdentifier: "stripe.com" (NO companyDataPoints — user did not ask for enrichments) | | "What's OpenAI's funding?" | companyIdentifier: "openai.com", companyDataPoints: [{ type: "Latest Funding" }] | | "Canva's competitors and tech stack" | companyIdentifier: "canva.com", companyDataPoints: [{ type: "Company Competitors" }, { type: "Tech Stack" }] | | "Notion's product roadmap" | companyIdentifier: "notion.so", companyDataPoints: [{ type: "Custom", customDataPoint: "product roadmap" }] |

Response Behavior

• Summarize the company result briefly (e.g., "Found Stripe").
• The tool returns a taskId for use with add-company-data-points, custom functions, or get-task-context.

Clay may render results in a widget in web chat hosts such as ChatGPT or claude.ai. Terminal/coding-agent hosts such as Codex, Claude Code, Cursor, Windsurf, and CLI environments do not show the widget. If you are unsure whether the widget is visible, assume it is not visible.

• If a widget is visible, avoid repeating the full widget contents unless the user asks for full contents; then call get-task-context with the taskId and answer inline.
• In terminal/coding-agent environments, when no widget is visible, or when the user asks for actual values/results, call get-task-context with the taskId and answer inline.
• Use get-task-context to poll until async results complete; if values are still in-progress, wait and retry rather than answering with missing values.
• If get-task-context is not available, fall back to get-task.

Search for contacts at a company by role, title, or department.

Quick Reference

• This tool: Find TYPES of people (e.g., "engineers at Stripe", "VPs at OpenAI")
• find-and-enrich-list-of-contacts: Find SPECIFIC named people (e.g., "John Smith at Stripe")
• Follow-ups: ALWAYS re-call this tool—never filter results in chat. When ambiguous, ask the user.

Parameters

companyIdentifier (required)

Domain (e.g., "stripe.com") or LinkedIn company URL. Company names alone will fail.

• Convert known companies: "Stripe" → "stripe.com"
• If ambiguous (e.g., "Delta"), ask the user to clarify

contactFilters (optional)

Narrow results. Only add filters the user explicitly requests.

Rules:

• Filters combine with AND; values within arrays combine with OR
• Keep compound titles as ONE string: "VP Finance" → ["VP Finance"], NOT ["VP", "Finance"]
• Use specific terms to avoid false matches:
• ✓ "Software Engineer" not "Engineer" (matches Sales Engineer, etc.)
• ✓ "Product Manager" not "Manager" (matches Account Manager, etc.)

Available filters: | Filter | Type | Description | |--------|------|-------------| | job_title_keywords | string[] | Titles to include | | job_title_exclude_keywords | string[] | Titles to exclude (e.g., ["Intern"]) | | profile_keywords | string[] | Keywords anywhere in the LinkedIn profile (headline, about, experience, etc.). Use for broad keyword searches, e.g. ["AI", "machine learning"] or ["founder", "co-founder"] | | certification_keywords | string[] | Certifications (e.g., ["AWS", "CPA"]) | | languages | string[] | Profile languages | | school_names | string[] | Schools attended | | current_role_min_months_since_start_date | number | Min months in role (tenured) | | current_role_max_months_since_start_date | number | Max months in role (new hires) | | locations | string[] | Locations to include (use formal names: "United States", "California") | | locations_exclude | string[] | Locations to exclude |

dataPoints (optional)

Enrich contacts/companies when creating a NEW search. For existing searches, use add-contact-data-points or add-company-data-points instead.

⚠️ CRITICAL: NEVER add data points unless the user EXPLICITLY asks for them. Enrichments cost credits. Only include data points when the user's message specifically requests that data.

• "Find engineers at Stripe" → NO data points
• "Find engineers at Stripe and get their emails" → add Email (user explicitly asked)
• "Tell me about OpenAI" → NO data points
• Do NOT add Headcount Growth, Recent News, or any other data point "to be helpful" — only what the user asked for

Structure: { contactDataPoints?: DataPoint[], companyDataPoints?: DataPoint[] }

DataPoint format:

• Standard: { type: "<DataPointType>" }
• Custom: { type: "Custom", customDataPoint: "<brief description>" }

Important: Only include customDataPoint field when type is "Custom"

Available contactDataPoints: Email, Summarize Work History, Find Thought Leadership

Available companyDataPoints: Headcount Growth, Recent News, Investors, Company Competitors, Company Customers, Tech Stack, Website Traffic, Open Jobs, Revenue Model, Annual Revenue, Latest Funding

Examples: | User request | dataPoints | |--------------|------------| | "engineers at Stripe" | NONE — user did not ask for enrichments | | "engineers at Stripe with emails" | { contactDataPoints: [{type: "Email"}] } | | "Canva's competitors and funding" | { companyDataPoints: [{type: "Company Competitors"}, {type: "Latest Funding"}] } | | "VPs at Figma with emails + company tech stack" | { contactDataPoints: [{type: "Email"}], companyDataPoints: [{type: "Tech Stack"}] } | | "Notion's product roadmap" (custom) | { companyDataPoints: [{type: "Custom", customDataPoint: "product roadmap"}] } |

Examples

| User says | Parameters | |-----------|------------| | "Find people at OpenAI" | companyIdentifier: "openai.com" | | "VP Finance at HubSpot" | companyIdentifier: "hubspot.com", contactFilters: { job_title_keywords: ["VP Finance"] } | | "VPs and Directors in California at HubSpot" | companyIdentifier: "hubspot.com", contactFilters: { job_title_keywords: ["VP", "Director"], locations: ["California"] } | | "Marketing managers outside the US at Salesforce" | companyIdentifier: "salesforce.com", contactFilters: { job_title_keywords: ["Marketing Manager"], locations_exclude: ["United States"] } | | "New hires at Stripe (last 3 months)" | companyIdentifier: "stripe.com", contactFilters: { current_role_max_months_since_start_date: 3 } | | "Find people mentioning AI at OpenAI" | companyIdentifier: "openai.com", contactFilters: { profile_keywords: ["AI", "artificial intelligence", "machine learning"] } | | "Find founders at YC companies" | companyIdentifier: "ycombinator.com", contactFilters: { profile_keywords: ["founder", "co-founder"] } |

Handling Follow-ups

ANY search modification requires re-calling this tool. Never filter in chat.

Interpret user intent:

• "also/too/as well" → ADD to existing filters
• "only/just" → NARROW within current context (e.g., "VPs only" after Finance search → "VP Finance")
• "actually/instead/switch" → REPLACE filters entirely
• When ambiguous, ask the user rather than guessing

Examples: 1. User: "Find SDRs at Verkada" → { job_title_keywords: ["SDR", "Sales Development"] } User: "Get AEs too" → ADD: { job_title_keywords: ["SDR", "Sales Development", "Account Executive"] }

2. User: "Find Finance people at Ramp" → { job_title_keywords: ["Finance"] } User: "Make it VPs only" → NARROW: { job_title_keywords: ["VP Finance"] }

3. User: "Find Finance people at Ramp" → { job_title_keywords: ["Finance"] } User: "Actually show me all VPs" → REPLACE: { job_title_keywords: ["VP"] }

Response Behavior

• Summarize the search briefly (e.g., "Found 20 engineers at OpenAI").
• The tool returns a taskId for use with add-contact-data-points, add-company-data-points, custom functions, or get-task-context.
• For emails/phones, use add-contact-data-points with the taskId.

Clay may render results in a widget in web chat hosts such as ChatGPT or claude.ai. Terminal/coding-agent hosts such as Codex, Claude Code, Cursor, Windsurf, and CLI environments do not show the widget. If you are unsure whether the widget is visible, assume it is not visible.

• If a widget is visible, avoid repeating the full widget contents unless the user asks for full contents; then call get-task-context with the taskId and answer inline.
• In terminal/coding-agent environments, when no widget is visible, or when the user asks for actual values/results, call get-task-context with the taskId and answer inline.
• Use get-task-context to poll until async results complete; if values are still in-progress, wait and retry rather than answering with missing values.
• If get-task-context is not available, fall back to get-task.

Zero Results

Suggest broadening in order: 1. Remove or broaden title keywords (e.g., "Software Engineer" → "Engineer") 2. Remove location filter 3. Remove tenure filter 4. Verify company domain is correct

Find and enrich specific named contacts at their companies.

Quick Reference

• This tool: Find SPECIFIC named people (e.g., "John Smith at OpenAI", "Jane Doe at Stripe")
• find-and-enrich-contacts-at-company: Find TYPES of people (e.g., "engineers at Stripe")
• Do NOT use if user only provides company names without contact names
• Do NOT use to enrich contacts already in an existing search — use add-contact-data-points with entityIds instead

Parameters

contacts (required)

Array of { contactName, companyIdentifier } objects.

• contactName: Full name (e.g., "John Smith")
• companyIdentifier: Domain or company LinkedIn URL (NOT person LinkedIn URLs)
• Domains: "openai.com", "stripe.com"
• LinkedIn: "linkedin.com/company/openai"
• Company names: Convert if confident (e.g., "Stripe" → "stripe.com"), otherwise ask user

dataPoints (optional)

Enrich contacts/companies when creating a NEW search. For existing searches, use add-contact-data-points or add-company-data-points instead.

⚠️ CRITICAL: NEVER add data points unless the user EXPLICITLY asks for them. Enrichments cost credits. Only include data points when the user's message specifically requests that data.

• "Find engineers at Stripe" → NO data points
• "Find engineers at Stripe and get their emails" → add Email (user explicitly asked)
• "Tell me about OpenAI" → NO data points
• Do NOT add Headcount Growth, Recent News, or any other data point "to be helpful" — only what the user asked for

Structure: { contactDataPoints?: DataPoint[], companyDataPoints?: DataPoint[] }

DataPoint format:

• Standard: { type: "<DataPointType>" }
• Custom: { type: "Custom", customDataPoint: "<brief description>" }

Important: Only include customDataPoint field when type is "Custom"

Available contactDataPoints: Email, Summarize Work History, Find Thought Leadership

Available companyDataPoints: Headcount Growth, Recent News, Investors, Company Competitors, Company Customers, Tech Stack, Website Traffic, Open Jobs, Revenue Model, Annual Revenue, Latest Funding

Examples: | User request | dataPoints | |--------------|------------| | "engineers at Stripe" | NONE — user did not ask for enrichments | | "engineers at Stripe with emails" | { contactDataPoints: [{type: "Email"}] } | | "Canva's competitors and funding" | { companyDataPoints: [{type: "Company Competitors"}, {type: "Latest Funding"}] } | | "VPs at Figma with emails + company tech stack" | { contactDataPoints: [{type: "Email"}], companyDataPoints: [{type: "Tech Stack"}] } | | "Notion's product roadmap" (custom) | { companyDataPoints: [{type: "Custom", customDataPoint: "product roadmap"}] } |

Examples

| User request | contacts | |--------------|----------| | "Find John Smith at OpenAI" | [{ contactName: "John Smith", companyIdentifier: "openai.com" }] | | "Look up Jane Doe at Stripe and Bob Lee at Figma" | [{ contactName: "Jane Doe", companyIdentifier: "stripe.com" }, { contactName: "Bob Lee", companyIdentifier: "figma.com" }] |

Follow-ups

• "Add [name] at [company] too" → Re-call with ALL contacts (previous + new)
• "Actually look up [different people]" → Re-call with only the new contacts

Response Behavior

• Summarize the search briefly (e.g., "Found 20 engineers at OpenAI").
• The tool returns a taskId for use with add-contact-data-points, add-company-data-points, custom functions, or get-task-context.
• For emails/phones, use add-contact-data-points with the taskId.

Clay may render results in a widget in web chat hosts such as ChatGPT or claude.ai. Terminal/coding-agent hosts such as Codex, Claude Code, Cursor, Windsurf, and CLI environments do not show the widget. If you are unsure whether the widget is visible, assume it is not visible.

• If a widget is visible, avoid repeating the full widget contents unless the user asks for full contents; then call get-task-context with the taskId and answer inline.
• In terminal/coding-agent environments, when no widget is visible, or when the user asks for actual values/results, call get-task-context with the taskId and answer inline.
• Use get-task-context to poll until async results complete; if values are still in-progress, wait and retry rather than answering with missing values.
• If get-task-context is not available, fall back to get-task.

Fetch the available dropdown options for a subroutine input that has a configured options source.

Check if credits are available for the workspace. Returns hasWorkspaceCredits, hasSalesRepCredits, and (when credit budgets are enabled) hasBudgetCredits.

Report which Clay workspace this connection is pinned to. Returns workspaceName, workspaceId, and workspaceUrl. Use when the user asks which workspace they are connected to, or to confirm where searches and enrichments will run.

Retrieve an existing search by task ID. This tool retrieves the current state of search results including any enrichments that have completed since the search was created.

When to Use This Tool

This is a private tool, the chat and user are not exposed to it.

Parameters

taskId (required)

• The task ID identifying the search to retrieve. This should be a taskId that was returned from a previous find-and-enrich-contacts-at-company or find-and-enrich-list-of-contacts tool call.

Search your Salesforce accounts synced to Clay. Returns accounts you own in Salesforce, with optional filters. Optionally scope results to a specific Clay Audiences segment.

Quick Reference

• This tool: Search YOUR Salesforce accounts (accounts where you are the owner)
• Optionally scope to a named audience segment (e.g., "Enterprise", "ICP")
• Requires Salesforce User and Account syncs to be configured in Clay Audiences

Parameters

audienceName (optional)

Name of a Clay Audiences segment to scope results to. When provided, only accounts that belong to the named segment AND are owned by you will be returned. Use this when the user mentions a specific audience, segment, or list name. Omit when the user just wants to search across all of their accounts.

filters (optional)

Narrow results by account attributes. All filters combine with AND (and are also AND-ed with the audience segment filter if provided).

| Filter | Type | Description | |--------|------|-------------| | companyName | string | Partial match on account name (e.g., "Acme") | | domain | string | Exact domain match (e.g., "acme.com"). Use the full domain, not a partial string. | | industry | string | Partial match on industry (e.g., "Technology") | | location | string | Match on headquarters location. Be specific: use a city name (e.g., "San Francisco"), state (e.g., "California"), or country (e.g., "United States") — not a combination. | | headcountMin | number | Minimum number of employees (inclusive, >=) | | headcountMax | number | Maximum number of employees (inclusive, <=) |

limit (optional)

Number of results to return. Default: 50, max: 100.

offset (optional)

Number of results to skip for pagination. Default: 0.

Examples

| User says | Parameters | |-----------|------------| | "Show me my accounts" | {} | | "My tech accounts" | { filters: { industry: "Technology" } } | | "Accounts in California with 100+ employees" | { filters: { location: "California", headcountMin: 100 } } | | "Find my account Acme Corp" | { filters: { companyName: "Acme" } } | | "Find acme.com" | { filters: { domain: "acme.com" } } | | "Accounts in my Enterprise segment" | { audienceName: "Enterprise" } | | "ICP accounts in San Francisco" | { audienceName: "ICP", filters: { location: "San Francisco" } } | | "My accounts from the Mid-Market audience with 50+ employees" | { audienceName: "Mid-Market", filters: { headcountMin: 50 } } |

Response Behavior

• Summarize results concisely (e.g., "Found 15 accounts matching your filters")
• List key details: account name, industry, and location
• Each account includes an accountId (numeric) that can be passed to ask-question-about-accounts for deeper analysis
• If zero results, suggest broadening filters or checking that Salesforce sync is configured
• If an audience name was provided but not found, suggest checking the segment name in Clay Audiences

Get task status and results by task ID. This tool handles all task types (search, direct) and returns the current state.

When to Use This Tool

This is a private tool used by the widget for polling task status.

Parameters

taskId (required)

• The task ID to retrieve. Accepts:
• Universal task IDs: mcp-task-* (from run_subroutine_direct, etc.)
• Legacy search IDs: cgas-search-id-* (backwards compatible)

page (optional)

• For direct tasks: 1-based page of entities (100 per page). Defaults to 1. The response includes totalEntities, hasMore, and overall completion status so callers don't need every entity to know the task state. isComplete means every entity finished (completed or errored), not that all succeeded.

Retrieve the current state of a task — all entities, enrichment values, and statuses.

When to Use

Call this when you need the actual data behind an entity to answer the user's question — e.g. the user asks "what's John's email?", "what X profiles did you get?", "show me the enrichment results", or any question about data that may have been enriched. The initial response from search/data-points tools only includes base fields (name, title, company, LinkedIn); ALL enrichment values (emails, X/Twitter profiles, work history, custom data points) are only available through this tool.

IMPORTANT: If the user asks about a data type and you don't see it in the initial search response, that does NOT mean it wasn't found — it means you need to call this tool to check.

Parameters

• taskId (required): Task ID from a previous tool call. Accepts mcp-task-* IDs and legacy cgas-* search IDs.
• entityIds (optional): Return only these entities.
• page (optional): For direct tasks (run_subroutine_direct), a 1-based page of entities — up to 100 per page. Defaults to 1. Ignored when entityIds is provided.

Response

Returns entities and their enrichment values for the task. Each enrichment has a name, state ("completed" / "in-progress" / "error"), and value.

Direct tasks are paginated: the response includes page, pageSize, totalEntities, and hasMore, plus processedEntities/isComplete for overall progress. isComplete means every entity finished (completed or errored), not that all succeeded. When hasMore is true, call again with the next page to retrieve more entities — or pass entityIds to fetch specific ones.

List available functions. Available functions: . Call this to see their required inputs before using run_subroutine.

Fetch the next page (up to 20 more results) of an existing search.

When to Use

Call this when the user wants MORE results than a search-contacts or search-companies call returned, and that search reported more were available (hasMore: true). Pass the taskId of the most recent page. Each page is a separate result set with its own taskId.

Only search-contacts and search-companies paginate. Not supported for search-contacts-by-name or the find-and-enrich tools; calling it on those returns an error.

Loading many results

Only loop this tool to pull multiple pages when the results feed analysis you'll do WITHOUT the widget — summarizing, counting, ranking, comparing, or feeding another tool — where you genuinely need every row. Fetch pages in sequence until you have enough (or hasMore is false), and don't render.

If the user just wants to SEE the results, do NOT pre-load pages: render the first page with render-search-results and let them paginate inside the widget, which has its own paging controls. Even for a large ask ("get me 100 people"), a single page plus in-widget pagination is the right response when the end goal is viewing — don't call this several times before rendering.

Parameters

• taskId (required): The taskId of the current page of results (mcp-task-* or legacy cgas-search-id-*).

Response

Data only — this does NOT render a widget. Returns the next page's results and a NEW taskId. If the user wants to SEE the page, call render-search-results with that new taskId. Use it to enrich or to load the page after it as well. hasMore indicates whether further pages remain.

Query audience accounts, contacts, or deals using natural language. This tool translates your description into a structured filter, validates it against the database, and returns matching entities with their field values.

Parameters

query (required)

Describe what you're looking for in plain language. The tool automatically determines whether you're querying accounts, contacts, or deals.

audienceName (optional, string)

Name of a saved audience segment to scope results to. The query filter is applied within this segment.

onlyMine (optional, boolean)

When true, restrict results to accounts owned by the calling user in Salesforce. Only applies when the query targets accounts.

limit (optional, default 50, max 100)

Max number of rows returned. Keep below 100 to stay LLM-context friendly.

offset (optional, default 0)

Pagination offset. Increment by limit to fetch additional pages.

Response

{ entityType, explanation, totalMatched, accounts | contacts }

• entityType: The detected entity type (ACCOUNT or CONTACT)
• explanation: Human-readable summary of the applied filter
• totalMatched: Total entities matching the filter
• Each entity carries its entityId, externalRecordId, and fields (keyed by display name) with values

Examples

| User says | query parameter | |-----------|----------------| | "Show me my healthcare accounts" | "healthcare accounts" (+ onlyMine: true) | | "Find contacts whose title is VP Engineering" | "contacts with title VP Engineering" | | "Accounts with open opportunities over $100k" | "accounts with opportunities over $100k" | | "VPs at tech companies with 500+ employees" | "VPs at tech companies with 500+ employees" | | "Healthcare accounts in my Enterprise Target list" | "healthcare accounts" (+ audienceName: "Enterprise Target") |

Notes

• No need to discover field IDs first — this tool handles field discovery internally
• If the filter cannot be constructed from your description, a descriptive error is returned
• For deep analysis of specific accounts (contacts, emails, calls), use ask-question-about-accounts with the account IDs from this tool's results

Render previously-fetched results as a widget for the user to see.

When to Use

Call this by DEFAULT after a search-contacts, search-contacts-by-name, or search-companies call to show the user the results — a plain find/search/list request means they want to see them. Pass the taskId returned by that tool. Don't ask the user whether to render; just render.

Only skip rendering when the search was an intermediate step (collecting data for another tool, enriching, filtering, or aggregating) and the user did not ask to see a list — then use the data directly instead. You can always render later if the user then asks to see the results.

add-contact-data-points, add-company-data-points, and run_subroutine_direct already return the widget themselves — do NOT call this after them.

Parameters

• taskId (required): The taskId returned by a search-* tool (mcp-task-* or legacy cgas-search-id-*).

Response

Returns the results for the task (companies and contacts for searches, or entities for direct tasks).

Execute a function on contacts/companies FROM AN EXISTING SEARCH ().

STOP! Choose the right tool:

• User gave you specific values (LinkedIn URL, name, email)? → Use run_subroutine_direct instead!
• User wants to run on contacts from a previous search? → Use THIS tool (run_subroutine)

Usage (only if you have a taskId from a previous search)

• Single contact: pass taskId + entityIds + fieldMapping
• All contacts: pass taskId + fieldMapping

fieldMapping format

Format: { "entityField": "subroutineInput" }

• KEY = entity field name (from contact data, e.g. "name", "url", "domain")
• VALUE = subroutine input name (from list_subroutines, e.g. "full_name", "linkedin_url")

Example: {"name": "full_name", "url": "linkedin_url", "domain": "company_domain"}

IMPORTANT

Do NOT try to generate or summarize the function results yourself from your own knowledge. Clay may render results in a widget in hosts that support MCP Apps, such as ChatGPT, claude.ai, and Cursor. Other terminal/coding-agent hosts such as Codex, Claude Code, Windsurf, and CLI environments do not show the widget. If you are unsure whether the widget is visible, assume it is not visible.

• If a widget is visible, avoid repeating the full widget contents unless the user asks for full contents; then call get-task-context with the taskId and answer inline.
• In terminal/coding-agent environments, when no widget is visible, or when the user asks for actual values/results, call get-task-context with the taskId and answer inline.
• NEVER tell the user that data was not found, not returned, or unavailable without first calling get-task-context. The initial search/tool response only includes base fields — enrichment results (emails, X/Twitter profiles, work history, custom data points, etc.) are only available via get-task-context.
• When the user asks about a specific value (e.g. "what's Patrick's email?", "what X profiles did you get?"), call get-task-context FIRST to check if the data has already been enriched — the user may have triggered enrichments through the widget. Only call add-contact-data-points / add-company-data-points if get-task-context shows the enrichment hasn't been run yet.
• Use get-task-context to poll until async results complete; if values are still in-progress, wait and retry rather than answering with missing values.
• If get-task-context is not available, fall back to get-task.

Execute a custom function on one or more sets of provided inputs. NO existing task or entityIds needed.

When to Use This Tool

Use this tool when the user provides specific input values (like a LinkedIn URL, name, email, or a list of domains) and wants to run a function on that data directly. This is the PREFERRED tool when the user gives you concrete values to work with — for one value or many.

When NOT to Use This Tool

Do NOT use this tool if you need to run on contacts from an existing search. Use run_subroutine instead for batch operations on search results.

Usage

Provide:

• subroutine_id: from list_subroutines
• inputs: an ARRAY of input objects, one per run. Each object's keys must match the input names from list_subroutines. Use a single-element array to run once.

Example (one): [{"Linkedin URL": "https://linkedin.com/in/someone"}] Example (many): [{"Domain": "clay.com"}, {"Domain": "google.com"}]

IMPORTANT

Each input set consumes credits (N sets = N runs). Do NOT try to generate or summarize the function results yourself from your own knowledge. Clay may render results in a widget in hosts that support MCP Apps, such as ChatGPT, claude.ai, and Cursor. Other terminal/coding-agent hosts such as Codex, Claude Code, Windsurf, and CLI environments do not show the widget. If you are unsure whether the widget is visible, assume it is not visible.

• If a widget is visible, avoid repeating the full widget contents unless the user asks for full contents; then call get-task-context with the taskId and answer inline.
• In terminal/coding-agent environments, when no widget is visible, or when the user asks for actual values/results, call get-task-context with the taskId and answer inline.
• NEVER tell the user that data was not found, not returned, or unavailable without first calling get-task-context. The initial search/tool response only includes base fields — enrichment results (emails, X/Twitter profiles, work history, custom data points, etc.) are only available via get-task-context.
• When the user asks about a specific value (e.g. "what's Patrick's email?", "what X profiles did you get?"), call get-task-context FIRST to check if the data has already been enriched — the user may have triggered enrichments through the widget. Only call add-contact-data-points / add-company-data-points if get-task-context shows the enrichment hasn't been run yet.
• Use get-task-context to poll until async results complete; if values are still in-progress, wait and retry rather than answering with missing values.
• If get-task-context is not available, fall back to get-task.

Response Behavior

Confirm briefly: "Running [function name]—results will appear shortly."

Run a custom subroutine on search entities. The backend automatically generates the field mapping.

Find a LIST of companies matching prospecting filters (industry, size, location, funding, tech stack, keywords), expressed as a Search DSL query. This searches PUBLICLY AVAILABLE company data — it is NOT for the user's own account/CRM data.

Quick Reference

• This tool: Find companies by CRITERIA (e.g. "fintech companies in NYC with 50-200 employees",

"Series B SaaS companies using Salesforce").

• search-contacts: Find TYPES of people at a company (e.g. "engineers at Stripe").
• search-contacts-by-name: Find SPECIFIC named people (e.g. "John Smith at Stripe").
• query-objects + ask-question-about-accounts: Ask about the user's OWN accounts/deals/CRM.

Parameters

dslQuery (required)

A Search DSL query that MUST start with select from companies. Translate the user's natural-language prospecting request into filters. Only filter on what the user explicitly asks for.

Search DSL

Write a single Search DSL query. Grammar:

query    = "select" "from" entity where? limit_by? limit?
entity   = "people" | "companies"
where    = "where" predicate
limit_by = "limit" POSITIVE_INT "by" "clay_company_id"   (people only)
limit    = "limit" INTEGER

predicate = or_expr
or_expr   = and_expr ("or" and_expr)*
and_expr  = unary ("and" unary)*
unary     = "not" unary | comparison | aggregate | "(" predicate ")"

comparison = field op value | field "is_null" | field "is_not_null"
op    = "=" | "!=" | "<" | "<=" | ">" | ">=" | "contains" | "starts_with"
    | "ends_with" | "in" | "not_in" | "is_similar_to"
value = STRING | NUMBER | BOOLEAN | "(" value ("," value)* ")" | date_expr
date_expr = "today" "(" ")" (("+" | "-") "interval" POSITIVE_INT unit)?
unit  = "day[s]" | "week[s]" | "month[s]" | "year[s]"

Operators

• contains is whole-token match (not substring); list form: field contains ("a", "b").
• in / not_in take a value list; enum fields support only =, !=, in, not_in.
• is_similar_to expands meaning (e.g. job_title is_similar_to ("VP Sales")).
• and binds tighter than or; group with parentheses.

Limits

• Add limit N only when the user asks for a specific total count.
• limit N by clay_company_id (people queries only) caps results per company.

Company fields

• domain (string): Company website domain, e.g. 'google.com', 'stripe.com'.
• description (string): Company description. Use contains for keyword matching.
• products_and_services (string): What the company does, makes, and sells, matched semantically against company document embeddings. Only supports is_similar_to with one or more non-empty string values; multiple values match companies similar to ANY value (e.g. products_and_services is_similar_to ("b2b saas", "crm")). Distinct from description keyword matching; not all companies have embeddings, and rows without one never match.
• company_type (string, enum): Company type classification. Values: "Privately Held" (Privately held), "Public Company" (Public company), "Partnership", "Self Employed" (Self-employed), "Non Profit" (Nonprofit), "Educational", "Self Owned" (Self-owned), "Government Agency" (Government agency)
• company_size (string, enum): Company size range bucket. Prefer this for first-pass company-size filtering; use estimated_employee_count only when the user explicitly asks for exact employee count/headcount. Values: "1" (1 employee), "2-10" (2–10 employees), "11-50" (11–50 employees), "51-200" (51–200 employees), "201-500" (201–500 employees), "501-1,000" (501–1,000 employees), "1,001-5,000" (1,001–5,000 employees), "5,001-10,000" (5,001–10,000 employees), "10,001+" (10,001+ employees)
• estimated_employee_count (number): Estimated total employee count. Use only when the user explicitly asks for exact employee count/headcount or asks to switch from company-size buckets to exact counts.
• estimated_follower_count (number): Estimated social media audience/follower count.
• year_founded (year): Year the company was founded.
• employee_growth_3mo (number): Employee growth ratio (1.1 = +10% growth, 0.9 = −10% decline).
• employee_growth_6mo (number): Employee growth ratio (1.1 = +10% growth, 0.9 = −10% decline).
• employee_growth_12mo (number): Employee growth ratio (1.1 = +10% growth, 0.9 = −10% decline).
• employee_growth_24mo (number): Employee growth ratio (1.1 = +10% growth, 0.9 = −10% decline).
• annual_revenue (string, enum): Annual revenue bracket. Use = or in with exact bucket values, not numeric operators. Values: "0-500K" ($0–$500K), "500K-1M" ($500K–$1M), "1M-5M" ($1M–$5M), "5M-10M" ($5M–$10M), "10M-25M" ($10M–$25M), "25M-75M" ($25M–$75M), "75M-200M" ($75M–$200M), "200M-500M" ($200M–$500M), "500M-1B" ($500M–$1B), "1B-10B" ($1B–$10B), "10B-100B" ($10B–$100B), "100B-1T" ($100B+)
• ai_business_types (string): Derived business model type. LOW COVERAGE — treat as optional: always pair with an is_null fallback, e.g. (ai_business_types contains "B2B" or ai_business_types is_null). Use contains for matching. Common: "B2B", "B2C", "Nonprofit"
• industry (string, enum): The company's main industry. This is the primary, structured way to filter companies by industry. Values: "Abrasives and Nonmetallic Minerals Manufacturing", "Accessible Architecture and Design", "Accommodation Services", "Accounting", "Administration of Justice", "Administrative and Support Services", "Advertising Services", "Agricultural Chemical Manufacturing", "Agriculture, Construction, Mining Machinery Manufacturing", "Air, Water, and Waste Program Management", "Airlines and Aviation", "Alternative Dispute Resolution", "Alternative Medicine", "Ambulance Services", "Amusement Parks and Arcades", "Animal Feed Manufacturing", "Animation", "Animation and Post-production", "Apparel Manufacturing", "Apparel and Fashion", "Appliances, Electrical, and Electronics Manufacturing", "Architectural and Structural Metal Manufacturing", "Architecture and Planning", "Armed Forces", "Artists and Writers", "Arts and Crafts", "Audio and Video Equipment Manufacturing", "Automation Machinery Manufacturing", "Automotive", "Aviation & Aerospace", "Aviation and Aerospace Component Manufacturing", "Baked Goods Manufacturing", "Banking", "Bars, Taverns, and Nightclubs", "Bed-and-Breakfasts, Hostels, Homestays", "Beverage Manufacturing", "Biomass Electric Power Generation", "Biotechnology", "Biotechnology Research", "Blockchain Services", "Blogs", "Boilers, Tanks, and Shipping Container Manufacturing", "Book Publishing", "Book and Periodical Publishing", "Breweries", "Broadcast Media Production and Distribution", "Building Construction", "Building Equipment Contractors", "Building Finishing Contractors", "Building Materials", "Building Structure and Exterior Contractors", "Business Consulting and Services", "Business Content", "Business Intelligence Platforms", "Business Supplies and Equipment", "Capital Markets", "Caterers", "Chemical Manufacturing", "Chemical Raw Materials Manufacturing", "Child Day Care Services", "Chiropractors", "Civic and Social Organizations", "Civil Engineering", "Claims Adjusting, Actuarial Services", "Clay and Refractory Products Manufacturing", "Climate Data and Analytics", "Climate Technology Product Manufacturing", "Coal Mining", "Collection Agencies", "Commercial Real Estate", "Commercial and Industrial Equipment Rental", "Commercial and Industrial Machinery Maintenance", "Commercial and Service Industry Machinery Manufacturing", "Communications Equipment Manufacturing", "Community Development and Urban Planning", "Community Services", "Computer Games", "Computer Hardware", "Computer Hardware Manufacturing", "Computer Networking", "Computer Networking Products", "Computer and Network Security", "Computers and Electronics Manufacturing", "Conservation Programs", "Construction", "Construction Hardware Manufacturing", "Consumer Electronics", "Consumer Goods", "Consumer Goods Rental", "Consumer Services", "Cosmetics", "Cosmetology and Barber Schools", "Courts of Law", "Credit Intermediation", "Dairy", "Dairy Product Manufacturing", "Dance Companies", "Data Infrastructure and Analytics", "Data Security Software Products", "Defense & Space", "Defense and Space Manufacturing", "Dentists", "Design", "Design Services", "Desktop Computing Software Products", "Digital Accessibility Services", "Distilleries", "E-Learning", "E-Learning Providers", "Economic Programs", "Education", "Education Administration Programs", "Education Management", "Electric Lighting Equipment Manufacturing", "Electric Power Generation", "Electric Power Transmission, Control, and Distribution", "Electrical Equipment Manufacturing", "Electronic and Precision Equipment Maintenance", "Embedded Software Products", "Emergency and Relief Services", "Engineering Services", "Engines and Power Transmission Equipment Manufacturing", "Entertainment", "Entertainment Providers", "Environmental Quality Programs", "Environmental Services", "Equipment Rental Services", "Events Services", "Executive Offices", "Executive Search Services", "Fabricated Metal Products", "Facilities Services", "Farming, Ranching, Forestry", "Farming", "Fashion Accessories Manufacturing", "Financial Services", "Fine Art", "Fine Arts Schools", "Fire Protection", "Fisheries", "Flight Training", "Food & Beverages", "Food and Beverage Manufacturing", "Food and Beverage Retail", "Food and Beverage Services", "Food Production", "Footwear Manufacturing", "Forestry and Logging", "Freight and Package Transportation", "Fruit and Vegetable Preserves Manufacturing", "Fundraising", "Funds and Trusts", "Furniture", "Furniture and Home Furnishings Manufacturing", "Gambling Facilities and Casinos", "Geothermal Electric Power Generation", "Glass Product Manufacturing", "Glass, Ceramics and Concrete Manufacturing", "Golf Courses and Country Clubs", "Government Administration", "Government Relations", "Government Relations Services", "Graphic Design", "Ground Passenger Transportation", "HVAC and Refrigeration Equipment Manufacturing", "Health and Human Services", "Health, Wellness and Fitness", "Higher Education", "Highway, Street, and Bridge Construction", "Historical Sites", "Holding Companies", "Home Health Care Services", "Horticulture", "Hospitality", "Hospitals", "Hospitals and Health Care", "Hotels and Motels", "Household Appliance Manufacturing", "Household Services", "Household and Institutional Furniture Manufacturing", "Housing Programs", "Housing and Community Development", "Human Resources", "Human Resources Services", "Hydroelectric Power Generation", "IT Services and IT Consulting", "IT System Custom Software Development", "IT System Data Services", "IT System Design Services", "IT System Installation and Disposal", "IT System Operations and Maintenance", "IT System Testing and Evaluation", "IT System Training and Support", "Import and Export", "Individual and Family Services", "Industrial Automation", "Industrial Machinery Manufacturing", "Industry Associations", "Information Services", "Information Technology and Services", "Insurance", "Insurance Agencies and Brokerages", "Insurance Carriers", "Insurance and Employee Benefit Funds", "Interior Design", "International Affairs", "International Trade and Development", "Internet Marketplace Platforms", "Internet News", "Internet Publishing", "Investment Advice", "Investment Banking", "Investment Management", "Janitorial Services", "Landscaping Services", "Language Schools", "Laundry and Drycleaning Services", "Law Enforcement", "Law Practice", "Leasing Non-residential Real Estate", "Leasing Residential Real Estate", "Leather Product Manufacturing", "Legal Services", "Legislative Offices", "Leisure, Travel & Tourism", "Libraries", "Loan Brokers", "Luxury Goods and Jewelry", "Machinery Manufacturing", "Manufacturing", "Maritime", "Maritime Transportation", "Market Research", "Marketing Services", "Mattress and Blinds Manufacturing", "Measuring and Control Instrument Manufacturing", "Meat Products Manufacturing", "Mechanical or Industrial Engineering", "Media & Telecommunications", "Media Production", "Medical Devices", "Medical Equipment Manufacturing", "Medical Practices", "Medical and Diagnostic Laboratories", "Mental Health Care", "Metal Ore Mining", "Metal Treatments", "Metal Valve, Ball, and Roller Manufacturing", "Metalworking Machinery Manufacturing", "Military and International Affairs", "Mining", "Mobile Computing Software Products", "Mobile Food Services", "Mobile Gaming Apps", "Motor Vehicle Manufacturing", "Motor Vehicle Parts Manufacturing", "Movies and Sound Recording", "Movies, Videos and Sound", "Museums", "Museums, Historical Sites, and Zoos", "Music", "Musicians", "Nanotechnology Research", "Natural Gas Distribution", "Newspaper Publishing", "Non-profit Organization Management", "Non-profit Organizations", "Nonmetallic Mineral Mining", "Nonresidential Building Construction", "Nuclear Electric Power Generation", "Nursing Homes and Residential Care Facilities", "Office Administration", "Office Furniture and Fixtures Manufacturing", "Oil and Gas", "Oil, Gas, and Mining", "Online Audio and Video Media", "Online Media", "Online and Mail Order Retail", "Operations Consulting", "Optometrists", "Outpatient Care Centers", "Outsourcing and Offshoring Consulting", "Outsourcing/Offshoring", "Packaging and Containers", "Packaging and Containers Manufacturing", "Paint, Coating, and Adhesive Manufacturing", "Paper and Forest Product Manufacturing", "Paper and Forest Products", "Performing Arts", "Performing Arts and Spectator Sports", "Periodical Publishing", "Personal Care Product Manufacturing", "Personal Care Services", "Personal and Laundry Services", "Pet Services", "Pharmaceutical Manufacturing", "Philanthropic Fundraising Services", "Philanthropy", "Photography", "Physical, Occupational and Speech Therapists", "Physicians", "Plastics Manufacturing", "Plastics and Rubber Product Manufacturing", "Political Organizations", "Primary Metal Manufacturing", "Primary and Secondary Education", "Printing Services", "Professional Organizations", "Professional Services", "Professional Training and Coaching", "Program Development", "Public Assistance Programs", "Public Health", "Public Policy", "Public Policy Offices", "Public Relations and Communications Services", "Public Safety", "Radio and Television Broadcasting", "Rail Transportation", "Railroad Equipment Manufacturing", "Ranching", "Real Estate", "Real Estate Agents and Brokers", "Real Estate and Equipment Rental Services", "Recreational Facilities", "Religious Institutions", "Renewable Energy Equipment Manufacturing", "Renewable Energy Power Generation", "Renewable Energy Semiconductor Manufacturing", "Renewables & Environment", "Repair and Maintenance", "Research", "Research Services", "Residential Building Construction", "Restaurants", "Retail", "Retail Apparel and Fashion", "Retail Appliances, Electrical, and Electronic Equipment", "Retail Art Dealers", "Retail Art Supplies", "Retail Books and Printed News", "Retail Building Materials and Garden Equipment", "Retail Florists", "Retail Furniture and Home Furnishings", "Retail Gasoline", "Retail Groceries", "Retail Health and Personal Care Products", "Retail Luxury Goods and Jewelry", "Retail Motor Vehicles", "Retail Musical Instruments", "Retail Office Equipment", "Retail Office Supplies and Gifts", "Retail Pharmacies", "Retail Recyclable Materials & Used Merchandise", "Reupholstery and Furniture Repair", "Robotics Engineering", "Rubber Products Manufacturing", "Satellite Telecommunications", "School and Employee Bus Services", "Seafood Product Manufacturing", "Securities and Commodity Exchanges", "Security Guards and Patrol Services", "Security Systems Services", "Security and Investigations", "Semiconductor Manufacturing", "Semiconductors", "Services for Renewable Energy", "Services for the Elderly and Disabled", "Sheet Music Publishing", "Shipbuilding", "Shuttles and Special Needs Transportation Services", "Sightseeing Transportation", "Soap and Cleaning Product Manufacturing", "Social Networking Platforms", "Software Development", "Solar Electric Power Generation", "Sound Recording", "Space Research and Technology", "Specialty Trade Contractors", "Spectator Sports", "Sporting Goods", "Sporting Goods Manufacturing", "Sports Teams and Clubs", "Sports and Recreation Instruction", "Spring and Wire Product Manufacturing", "Staffing and Recruiting", "Steam and Air-Conditioning Supply", "Strategic Management Services", "Subdivision of Land", "Sugar and Confectionery Product Manufacturing", "Surveying and Mapping Services", "Taxi and Limousine Services", "Technical and Vocational Training", "Technology, Information and Internet", "Technology, Information and Media", "Telecommunications", "Telecommunications Carriers", "Telephone Call Centers", "Temporary Help Services", "Textile Manufacturing", "Theater Companies", "Think Tanks", "Tobacco", "Tobacco Manufacturing", "Translation and Localization", "Transportation Equipment Manufacturing", "Transportation Programs", "Transportation, Logistics, Supply Chain and Storage", "Transportation/Trucking/Railroad", "Travel Arrangements", "Truck Transportation", "Trusts and Estates", "Turned Products and Fastener Manufacturing", "Urban Transit Services", "Utilities", "Utilities Administration", "Utility System Construction", "Vehicle Repair and Maintenance", "Venture Capital and Private Equity Principals", "Veterinary", "Veterinary Services", "Vocational Rehabilitation Services", "Warehousing", "Warehousing and Storage", "Waste Collection", "Waste Treatment and Disposal", "Water Supply and Irrigation Systems", "Water, Waste, Steam, and Air Conditioning Services", "Wellness and Fitness Services", "Wholesale", "Wholesale Alcoholic Beverages", "Wholesale Apparel and Sewing Supplies", "Wholesale Appliances, Electrical, and Electronics", "Wholesale Building Materials", "Wholesale Chemical and Allied Products", "Wholesale Computer Equipment", "Wholesale Drugs and Sundries", "Wholesale Food and Beverage", "Wholesale Footwear", "Wholesale Furniture and Home Furnishings", "Wholesale Hardware, Plumbing, Heating Equipment", "Wholesale Import and Export", "Wholesale Luxury Goods and Jewelry", "Wholesale Machinery", "Wholesale Metals and Minerals", "Wholesale Motor Vehicles and Parts", "Wholesale Paper Products", "Wholesale Petroleum and Petroleum Products", "Wholesale Raw Farm Products", "Wholesale Recyclable Materials", "Wind Electric Power Generation", "Wine and Spirits", "Wineries", "Wireless Services", "Wood Product Manufacturing", "Writing and Editing", "Zoos and Botanical Gardens"
• naics_codes_2022 (string, enum, array): NAICS 2022 industry classification codes as numeric strings (2-6 digits). Matching is hierarchical: a code matches companies whose more specific codes fall under it (e.g. "5132" matches a company classified "513210"). Census publishes three 2-digit sectors as ranges: "31-33" (Manufacturing), "44-45" (Retail Trade), "48-49" (Transportation and Warehousing). Use = for one code, in for multiple, e.g. naics_codes_2022 in ("31-33", "541511"). Values: "11" (11: Agriculture, Forestry, Fishing and Hunting), "111" (111: Crop Production), "1111" (1111: Oilseed and Grain Farming), "11111" (11111: Soybean Farming), "111110" (111110: Soybean Farming), "11112" (11112: Oilseed (except Soybean) Farming), "111120" (111120: Oilseed (except Soybean) Farming), "11113" (11113: Dry Pea and Bean Farming), "111130" (111130: Dry Pea and Bean Farming), "11114" (11114: Wheat Farming), "111140" (111140: Wheat Farming), "11115" (11115: Corn Farming), "111150" (111150: Corn Farming), "11116" (11116: Rice Farming), "111160" (111160: Rice Farming), "11119" (11119: Other Grain Farming), "111191" (111191: Oilseed and Grain Combination Farming), "111199" (111199: All Other Grain Farming), "1112" (1112: Vegetable and Melon Farming), "11121" (11121: Vegetable and Melon Farming), …
• ai_industries (string, enum, array): AI-derived industry classification. Do NOT filter on this field unless the user explicitly asks for ai_industries — default vertical filtering uses industry. Use = for exact match, in for multiple. e.g. ai_industries = "Professional, Business and Legal Services". Values: "Agriculture, Forestry and Fisheries", "Automotive, Aerospace and Defense Manufacturing", "Education and Training", "Energy, Utilities and Environmental Services", "Finance and Insurance", "Healthcare and Life Sciences", "Hospitality, Food and Travel Services", "Industrial Manufacturing and Materials", "Media, Entertainment and Culture", "Non-Profit, Public Sector and Education (Non-Commercial)", "Personal and Home Services", "Professional, Business and Legal Services", "Real Estate and Construction", "Retail and Consumer Channels", "Software and IT", "Transportation and Logistics"
• ai_subindustries (string, enum, array): AI-derived subindustry classification. Use = for exact match, in for multiple. e.g. ai_subindustries = "AI and ML Platforms". Values: "AI and ML Platforms", "Agriculture and Forestry Software", "Blockchain and Web3", "Carriers and ISPs", "Cloud and Infrastructure Software", "Consumer Software", "Data and Analytics Software", "Developer Tools and Platforms", "Enterprise Software Solutions", "Financial Services Software", "Government and Public Sector Software", "Hardware and Networking", "Healthcare Software", "IoT and Embedded Systems Software", "IT Services and Cybersecurity", "Manufacturing Software", "Metaverse, AR/VR and Other Emerging Platforms", "Quantum Computing Software", "Real Estate and PropTech Software", "Retail and Ecommerce Software", "Security and Identity Software", "Biotechnology and Pharmaceuticals", "Digital Health and Telemedicine", "Hospitals, Clinics and Outpatient Care", "Medical Devices and Diagnostic Equipment", "Medical Testing and Clinical Laboratories", "Mental Health and Rehabilitation Services", "Pharma Distribution and CRO Services", "Banking and Lending", "Capital Markets and Cryptocurrency", "Cryptocurrency and Blockchain Services", "Financial Services Platforms", "Insurance and InsurTech", "Investment Management and WealthTech", "Venture Capital and Private Equity", "Electric Power and Grid Management", "Nuclear and Advanced Generation", "Oil and Gas Exploration, Production and Services", "Renewable Energy and Clean Tech", "Sustainability Tech and Environmental Consulting", "Water, Waste and Environmental Management", "3D Printing and Advanced Manufacturing", "Building Materials and Chemicals", "Consumer Goods and Appliances", "Electronics and Computer Equipment", "Food, Beverage and Tobacco Production", "Industrial Machinery and Equipment", "Mining, Metals and Natural Resources", "Architecture, Urban Planning and Green Building", "Commercial Real Estate Development and Leasing", "Construction and Civil Engineering Services", "Property and Facility Management", "Residential Real Estate Development and Brokerage", "Specialty Construction Products", "Automotive Service and Collision Repair", "Brick-and-Mortar Retail", "Media and Entertainment Retail", "Online Commerce and Marketplaces", "Retail Technology", "Specialty Auctions and Collectibles", "Wholesale and Distribution", "Autonomous Vehicles and Drone Delivery", "Car and Truck Rental", "Freight and Cargo", "Logistics Technology", "Passenger Transit and Mobility", "Warehousing, Fulfillment and 3PL Services", "Accounting, Audit and Financial Advisory", "Advertising, Marketing and Multimedia Design", "Defense and Government Services", "Facilities Management and Commercial Cleaning", "Human Resources, Staffing and Recruitment", "Legal Services and Regulatory Compliance", "Management Consulting and Strategy Consulting", "Translation, Document and Information Management", "Corporate Training and Learning and Development", "E-Learning Platforms and EdTech", "K-12 and Higher Education Institutions", "Test Prep, Tutoring and After-School Services", "Vocational Training and Certification Programs", "Digital Publishing and Streaming Platforms", "Film, Television and Broadcasting", "Gaming, Esports and Interactive Entertainment", "Live Events, Experiences and Ticketed Attractions", "Museums, Art Galleries and Cultural Preservation", "Music, Audio and Podcast Services", "Sports and Recreation", "Food and Beverage Services", "Hospitality and Lodging", "Travel Agencies and Leisure Services", "Funeral Homes and Related Services", "Home Services", "Personal Care and Wellness", "Veterinary Care and Pet Services", "AgriTech and Precision Farming", "Aquaculture and Fisheries", "Crop Farming and Livestock Production", "Farming Equipment and Supplies", "Forestry, Logging and Wood Products", "Mining and Extraction", "Aviation and Aerospace Component Manufacturing", "Automotive and Rental Retail", "Commercial Space Innovation", "Defense Systems and Marine Manufacturing", "Motor Vehicle and Parts Manufacturing", "Government Administration and Municipal Services", "NGOs, Charities and Community Organizations", "Public Healthcare and Social Services", "Public/Private Research Institutions and Educational Foundations", "Student Organizations and Campus Services"
• ai_revenue_streams (string, enum, array): AI-derived revenue stream classification. Do NOT filter on this field unless the user explicitly asks for revenue streams. Use = for exact match, in for multiple. e.g. ai_revenue_streams = "SaaS". Values: "Professional Services", "Financial Services", "Subscriptions/Recurring", "Product Sales", "Transaction Fees", "Rental/Leasing", "Project/Contract Work", "Event/Experience Revenue", "Grants/Donations", "Licensing/IP", "Advertising"
• locations (tuple array): All office locations. Use .any() or .count() with inner predicates on subfields.

Subfields:

• country_name (string, enum): Full country name, e.g. 'United States', 'Germany'. Values: "Afghanistan", "Albania", "Algeria", "Andorra", "Angola", "Anguilla", "Antarctica", "Antigua and Barbuda", "Argentina", "Armenia", "Aruba", "Australia", "Austria", "Azerbaijan", "Bahamas", "Bahrain", "Bangladesh", "Barbados", "Belarus", "Belgium", "Belize", "Benin", "Bermuda", "Bhutan", "Bolivia", "Bonaire, Saint Eustatius and Saba ", "Bosnia and Herzegovina", "Botswana", "Brazil", "British Virgin Islands", "Brunei", "Bulgaria", "Burkina Faso", "Burundi", "Cambodia", "Cameroon", "Canada", "Cape Verde", "Cayman Islands", "Central African Republic", "Chad", "Chile", "China", "Colombia", "Comoros", "Costa Rica", "Croatia", "Cuba", "Curacao", "Cyprus", "Czechia", "Democratic Republic of the Congo", "Denmark", "Djibouti", "Dominican Republic", "East Timor", "Ecuador", "Egypt", "El Salvador", "Equatorial Guinea", "Estonia", "Ethiopia", "Faroe Islands", "Fiji", "Finland", "France", "French Guiana", "French Polynesia", "Gabon", "Gambia", "Georgia", "Germany", "Ghana", "Gibraltar", "Greece", "Greenland", "Grenada", "Guadeloupe", "Guam", "Guatemala", "Guernsey", "Guinea", "Guyana", "Haiti", "Honduras", "Hong Kong", "Hungary", "Iceland", "India", "Indonesia", "Iran", "Iraq", "Ireland", "Isle of Man", "Israel", "Italy", "Ivory Coast", "Jamaica", "Japan", "Jersey", "Jordan", "Kazakhstan", "Kenya", "Kosovo", "Kuwait", "Kyrgyzstan", "Laos", "Latvia", "Lebanon", "Lesotho", "Liberia", "Libya", "Liechtenstein", "Lithuania", "Luxembourg", "Macao", "Macedonia", "Madagascar", "Malawi", "Malaysia", "Maldives", "Mali", "Malta", "Marshall Islands", "Martinique", "Mauritania", "Mauritius", "Mayotte", "Mexico", "Moldova", "Monaco", "Mongolia", "Montenegro", "Morocco", "Mozambique", "Myanmar", "Namibia", "Nepal", "Netherlands", "Netherlands Antilles", "New Caledonia", "New Zealand", "Nicaragua", "Niger", "Nigeria", "North Korea", "Northern Mariana Islands", "Norway", "Oman", "Pakistan", "Palestinian Territory", "Panama", "Papua New Guinea", "Paraguay", "Peru", "Philippines", "Poland", "Portugal", "Puerto Rico", "Qatar", "Republic of the Congo", "Reunion", "Romania", "Russia", "Rwanda", "Saint Barthelemy", "Saint Kitts and Nevis", "Saint Lucia", "Saint Vincent and the Grenadines", "Samoa", "San Marino", "Sao Tome and Principe", "Saudi Arabia", "Senegal", "Serbia", "Serbia and Montenegro", "Seychelles", "Sierra Leone", "Singapore", "Sint Maarten", "Slovakia", "Slovenia", "Somalia", "South Africa", "South Korea", "South Sudan", "Spain", "Sri Lanka", "Sudan", "Suriname", "Svalbard and Jan Mayen", "Swaziland", "Sweden", "Switzerland", "Syria", "Taiwan", "Tajikistan", "Tanzania", "Thailand", "Togo", "Tonga", "Trinidad and Tobago", "Tunisia", "Turkey", "Turkmenistan", "Turks and Caicos Islands", "U.S. Virgin Islands", "Uganda", "Ukraine", "United Arab Emirates", "United Kingdom", "United States", "Uruguay", "Uzbekistan", "Vanuatu", "Venezuela", "Vietnam", "Yemen", "Zambia", "Zimbabwe"
• city (string): City name, e.g. 'San Francisco', 'Berlin'. Common: "Aberdeen", "Abilene", "Akron", "Albany", "Albuquerque", "Alexandria", "Allentown", "Amarillo", "Anaheim", "Anchorage", "Ann Arbor", "Antioch", "Apple Valley", "Appleton", "Arlington", "Arvada", "Asheville", "Atlanta", "Atlantic City", "Augusta", …
• state_or_province (string): State, province, or first-level administrative district, e.g. 'California', 'Ontario'.
• postal_code (string): Postal or ZIP code, e.g. '94107'.
• region (string, enum): Business region for the office location. Values: "APAC", "EMEA", "LATAM", "NAM"
• is_headquarters (boolean): True when this location is the company headquarters (primary office).
• technographics (tuple array): Technology stack installed at the company, backed by BuyerCaddy data. Use .any() or .count() with inner predicates on subfields.

Subfields:

• vendor (string): Technology vendor name. Common: "Microsoft", "Google", "Amazon", "Adobe", "Oracle", "The PHP Group", "Facebook, Inc.", "Automattic Inc.", "Cloudflare", "Apache", "Meta Platforms, Inc"
• product (string): Product name. Common: "Amazon Web Services (AWS)", "Amazon Web Hosting", "Google Analytics 360", "PHP", "Google Tag Manager", "Microsoft 365 Apps & Services", "Google Marketing Platform", "Amazon EC2", "Microsoft Exchange", "GoDaddy Hosting"
• product_category (string): Top-level product category. Common: "IT Infrastructure", "Collaboration & Productivity", "Marketing", "Development", "Content Management", "Digital Advertising Tech", "Hosting", "CI/CD Tools", "Cloud Data Integration", "Web Hosting"

People predicate fields (inside people.exists(...) / people.count(...))

• job_title (string): Job title of the experience. Common: "Academic Counselor", "Accountant", "Account Executive", "Accounting Analyst", "Accounting Clerk", "Accounting Manager", "Accounting Partner", "Accounting Supervisor", "Account Manager", "Account Representative", "Accounts Payable Clerk", "Accounts Payable Manager", "Accounts Receivable Clerk", "Accounts Receivable Manager", "Account Supervisor", "Activities Director", "Activities Worker", "Actor", "Actuary", "Acupuncturist", …
• description (string): Experience description text. Use contains for keyword matching.
• company_name (string): Company name for the experience.
• employment_type (string): Type of employment. Common: "Full-time", "Part-time", "Internship", "Self-employed", "Contract", "Permanent", "Freelance", "Volunteer", "Other", "Temporary", "Apprenticeship"
• seniority (string, enum): Seniority level of the role. Values: "Founder", "Owner", "Board Member" (Board member), "Partner", "C-suite", "VP", "Director", "Head", "Manager", "Senior", "Mid-level", "Entry", "Intern / In Training" (Intern / in training), "Unknown"
• is_current (boolean): True if this is the person's current role, false for past roles. In experiences.any(...) on people queries, omit is_current to match any tenure. In people.exists(...) / people.count(...) on companies queries, include is_current = true by default when the user doesn't specify between current vs past.
• start_date (month): Date the experience started (YYYY-MM).
• end_date (month): Date the experience ended (YYYY-MM). Empty if current role.
• location (string): Free-text location of the experience.
• location_city (string): City of the experience, e.g. 'San Francisco'. Common: "Aberdeen", "Abilene", "Akron", "Albany", "Albuquerque", "Alexandria", "Allentown", "Amarillo", "Anaheim", "Anchorage", "Ann Arbor", "Antioch", "Apple Valley", "Appleton", "Arlington", "Arvada", "Asheville", "Atlanta", "Atlantic City", "Augusta", …
• location_state (string): State or province of the experience, e.g. 'California'.
• location_country (string, enum): Country of the experience, e.g. 'United States'. Values: "Afghanistan", "Åland Islands", "Albania", "Algeria", "American Samoa", "Andorra", "Angola", "Anguilla", "Antarctica", "Antigua and Barbuda", "Argentina", "Armenia", "Aruba", "Australia", "Austria", "Azerbaijan", "Bahamas", "Bahrain", "Bangladesh", "Barbados", "Belarus", "Belgium", "Belize", "Benin", "Bermuda", "Bhutan", "Bolivia", "Bosnia and Herzegovina", "Botswana", "Bouvet Island", "Brazil", "British Indian Ocean Territory", "Brunei Darussalam", "Bulgaria", "Burkina Faso", "Burundi", "Cambodia", "Cameroon", "Canada", "Cape Verde", "Cayman Islands", "Central African Republic", "Chad", "Chile", "China", "Christmas Island", "Cocos (Keeling) Islands", "Collectivity of Saint Martin", "Colombia", "Comoros", "Cook Islands", "Costa Rica", "Côte d'Ivoire", "Croatia", "Cuba", "Curaçao", "Cyprus", "Czech Republic", "Democratic Republic of the Congo", "Denmark", "Djibouti", "Dominica", "Dominican Republic", "Ecuador", "Egypt", "El Salvador", "Equatorial Guinea", "Eritrea", "Estonia", "Ethiopia", "Falkland Islands (Malvinas)", "Faroe Islands", "Fiji", "Finland", "France", "French Guiana", "French Polynesia", "French Southern Territories", "Gabon", "Gambia", "Georgia", "Germany", "Ghana", "Gibralta", "Greece", "Greenland", "Grenada", "Guadeloupe", "Guam", "Guatemala", "Guernsey", "Guinea-Bissau", "Guinea", "Guyana", "Haiti", "Heard Island and McDonald Islands", "Holy See", "Honduras", "Hong Kong", "Hungary", "Iceland", "India", "Indonesia", "Iran", "Iraq", "Ireland", "Isle of Man", "Israel", "Italy", "Jamaica", "Japan", "Jersey", "Jordan", "Kazakhstan", "Kenya", "Kiribati", "Kuwait", "Kyrgyzstan", "Laos", "Latvia", "Lebanon", "Lesotho", "Liberia", "Libya", "Liechtenstein", "Lithuania", "Luxembourg", "Macao", "Madagascar", "Malawi", "Malaysia", "Maldives", "Mali", "Malta", "Marshall Islands", "Martinique", "Mauritania", "Mauritius", "Mayotte", "Mexico", "Micronesia", "Moldova", "Monaco", "Mongolia", "Montenegro", "Montserrat", "Morocco", "Mozambique", "Myanmar", "Namibia", "Nauru", "Nepal", "Netherlands", "New Caledonia", "New Zealand", "Nicaragua", "Niger", "Nigeria", "Niue", "Norfolk Island", "North Korea", "North Macedonia", "Northern Mariana Islands", "Norway", "Oman", "Pakistan", "Palau", "Palestine", "Panama", "Papua New Guinea", "Paraguay", "Peru", "Philippines", "Pitcairn", "Poland", "Portugal", "Puerto Rico", "Qatar", "Republic of the Congo", "Réunion", "Romania", "Russia", "Rwanda", "Saint Barthélemy", "Saint Helena, Ascension and Tristan da Cunha", "Saint Kitts and Nevis", "Saint Lucia", "Saint Pierre and Miquelon", "Saint Vincent and the Grenadines", "Samoa", "San Marino", "Sao Tome and Principe", "Saudi Arabia", "Senegal", "Serbia", "Seychelles", "Sierra Leone", "Singapore", "Sint Maarten", "Slovakia", "Slovenia", "Solomon Islands", "Somalia", "South Africa", "South Georgia and the South Sandwich Islands", "South Korea", "South Sudan", "Spain", "Sri Lanka", "Sudan", "Suriname", "Swaziland", "Sweden", "Switzerland", "Syria", "Taiwan", "Tajikistan", "Tanzania", "Thailand", "Timor-Leste", "Togo", "Tokelau", "Tonga", "Trinidad and Tobago", "Tunisia", "Turkey", "Turkmenistan", "Turks and Caicos Islands", "Tuvalu", "Uganda", "Ukraine", "United Arab Emirates", "United Kingdom", "United States Minor Outlying Islands", "United States", "Uruguay", "Uzbekistan", "Vanuatu", "Venezuela", "Vietnam", "Virgin Islands, British", "Virgin Islands, U.S.", "Wallis and Futuna", "Western Sahara", "Yemen", "Zambia", "Zimbabwe"
• location_region (string, enum): Geographic region of the experience. Values: "APAC", "EMEA", "LATAM", "NAM"
• person.location_city (string): City where the person is located (their profile location, not the experience's), e.g. 'San Francisco'. Common: "Aberdeen", "Abilene", "Akron", "Albany", "Albuquerque", "Alexandria", "Allentown", "Amarillo", "Anaheim", "Anchorage", "Ann Arbor", "Antioch", "Apple Valley", "Appleton", "Arlington", "Arvada", "Asheville", "Atlanta", "Atlantic City", "Augusta", …
• person.location_state (string): State or province where the person is located (their profile location, not the experience's), e.g. 'California'.
• person.location_country (string, enum): Country where the person is located (their profile location, not the experience's), e.g. 'United States'. Values: "Afghanistan", "Åland Islands", "Albania", "Algeria", "American Samoa", "Andorra", "Angola", "Anguilla", "Antarctica", "Antigua and Barbuda", "Argentina", "Armenia", "Aruba", "Australia", "Austria", "Azerbaijan", "Bahamas", "Bahrain", "Bangladesh", "Barbados", "Belarus", "Belgium", "Belize", "Benin", "Bermuda", "Bhutan", "Bolivia", "Bosnia and Herzegovina", "Botswana", "Bouvet Island", "Brazil", "British Indian Ocean Territory", "Brunei Darussalam", "Bulgaria", "Burkina Faso", "Burundi", "Cambodia", "Cameroon", "Canada", "Cape Verde", "Cayman Islands", "Central African Republic", "Chad", "Chile", "China", "Christmas Island", "Cocos (Keeling) Islands", "Collectivity of Saint Martin", "Colombia", "Comoros", "Cook Islands", "Costa Rica", "Côte d'Ivoire", "Croatia", "Cuba", "Curaçao", "Cyprus", "Czech Republic", "Democratic Republic of the Congo", "Denmark", "Djibouti", "Dominica", "Dominican Republic", "Ecuador", "Egypt", "El Salvador", "Equatorial Guinea", "Eritrea", "Estonia", "Ethiopia", "Falkland Islands (Malvinas)", "Faroe Islands", "Fiji", "Finland", "France", "French Guiana", "French Polynesia", "French Southern Territories", "Gabon", "Gambia", "Georgia", "Germany", "Ghana", "Gibralta", "Greece", "Greenland", "Grenada", "Guadeloupe", "Guam", "Guatemala", "Guernsey", "Guinea-Bissau", "Guinea", "Guyana", "Haiti", "Heard Island and McDonald Islands", "Holy See", "Honduras", "Hong Kong", "Hungary", "Iceland", "India", "Indonesia", "Iran", "Iraq", "Ireland", "Isle of Man", "Israel", "Italy", "Jamaica", "Japan", "Jersey", "Jordan", "Kazakhstan", "Kenya", "Kiribati", "Kuwait", "Kyrgyzstan", "Laos", "Latvia", "Lebanon", "Lesotho", "Liberia", "Libya", "Liechtenstein", "Lithuania", "Luxembourg", "Macao", "Madagascar", "Malawi", "Malaysia", "Maldives", "Mali", "Malta", "Marshall Islands", "Martinique", "Mauritania", "Mauritius", "Mayotte", "Mexico", "Micronesia", "Moldova", "Monaco", "Mongolia", "Montenegro", "Montserrat", "Morocco", "Mozambique", "Myanmar", "Namibia", "Nauru", "Nepal", "Netherlands", "New Caledonia", "New Zealand", "Nicaragua", "Niger", "Nigeria", "Niue", "Norfolk Island", "North Korea", "North Macedonia", "Northern Mariana Islands", "Norway", "Oman", "Pakistan", "Palau", "Palestine", "Panama", "Papua New Guinea", "Paraguay", "Peru", "Philippines", "Pitcairn", "Poland", "Portugal", "Puerto Rico", "Qatar", "Republic of the Congo", "Réunion", "Romania", "Russia", "Rwanda", "Saint Barthélemy", "Saint Helena, Ascension and Tristan da Cunha", "Saint Kitts and Nevis", "Saint Lucia", "Saint Pierre and Miquelon", "Saint Vincent and the Grenadines", "Samoa", "San Marino", "Sao Tome and Principe", "Saudi Arabia", "Senegal", "Serbia", "Seychelles", "Sierra Leone", "Singapore", "Sint Maarten", "Slovakia", "Slovenia", "Solomon Islands", "Somalia", "South Africa", "South Georgia and the South Sandwich Islands", "South Korea", "South Sudan", "Spain", "Sri Lanka", "Sudan", "Suriname", "Swaziland", "Sweden", "Switzerland", "Syria", "Taiwan", "Tajikistan", "Tanzania", "Thailand", "Timor-Leste", "Togo", "Tokelau", "Tonga", "Trinidad and Tobago", "Tunisia", "Turkey", "Turkmenistan", "Turks and Caicos Islands", "Tuvalu", "Uganda", "Ukraine", "United Arab Emirates", "United Kingdom", "United States Minor Outlying Islands", "United States", "Uruguay", "Uzbekistan", "Vanuatu", "Venezuela", "Vietnam", "Virgin Islands, British", "Virgin Islands, U.S.", "Wallis and Futuna", "Western Sahara", "Yemen", "Zambia", "Zimbabwe"
• person.location_region (string, enum): Geographic region where the person is located (their profile location, not the experience's). Values: "APAC", "EMEA", "LATAM", "NAM"
• person.headline (string): Profile headline (the tagline below their name). Use contains for keyword matching.
• person.about (string): About/summary section of the profile. Use contains for keyword matching.
• person.languages (string, array): Languages listed on the person's profile. Use = for exact match, in for multiple. e.g. person.languages = "Spanish". Common: "English", "Spanish", "French", "German", "Portuguese", "Chinese", "Japanese", "Hindi", "Arabic", "Korean", "Italian", "Dutch", "Russian"
• person.years_of_experience (number): Estimated full-time years of experience based on full-time roles on the profile.
• person.full_name (string): Full name of the person (first and last).
• person.network_size (number): Estimated professional network size (connection count).
• person.estimated_follower_count (number): Estimated social media audience/follower count.
• person.education (tuple array): The person's education history (school, degree, field of study, dates, description, activities). Use person.education.any(...) or person.education.count(...) with inner predicates on subfields.

Subfields:

• school_name (string): Name of the school or university.
• degree (string): Degree obtained, e.g. 'Bachelor of Science', 'Master of Business Administration', 'PhD'.
• field_of_study (string): Academic major or field, e.g. 'Computer Science', 'Economics', 'Mechanical Engineering'.
• start_date (month): Date education started (YYYY-MM).
• end_date (month): Date education ended (YYYY-MM).
• description (string): Education description text. Use contains for keyword matching.
• activities_and_societies (string): Activities and societies during education. Use contains for keyword matching.

Jobs predicate fields (inside jobs.exists(...) / jobs.count(...))

• job_title (string): Job posting title. Common: "Academic Counselor", "Accountant", "Account Executive", "Accounting Analyst", "Accounting Clerk", "Accounting Manager", "Accounting Partner", "Accounting Supervisor", "Account Manager", "Account Representative", "Accounts Payable Clerk", "Accounts Payable Manager", "Accounts Receivable Clerk", "Accounts Receivable Manager", "Account Supervisor", "Activities Director", "Activities Worker", "Actor", "Actuary", "Acupuncturist", …
• job_description (string): Full job description text. Use contains for keyword matching.
• employment_type (string, enum): Type of employment. Values: "Full-time", "Part-time", "Contract", "Internship", "Temporary", "Other", "Volunteer"
• seniority (string, enum): Seniority level of the job posting. Values: "Executive", "Entry level", "Mid-Senior level", "Not Applicable", "Internship", "Associate", "Director"
• location (string): Free-text job location.
• job_posted_date (date): Date the job was posted.
• job_removed_date (date): Date the job listing was removed.
• job_still_open (boolean): True if the job posting is currently open, false if it closed within the last 6 months. Default to job_still_open = true unless the user explicitly asks for past/closed/historical postings, or asks about job posting history over a time range.
• recruiter_name (string): Name of the recruiter for this posting.

Examples

| User says | dslQuery | |-----------|----------| | "fintech companies in NYC with 50-200 employees" | select from companies where industry in ("Financial Services", "Banking") and estimated_employee_count >= 50 and estimated_employee_count <= 200 and locations.any(city = "New York") | | "Series B SaaS companies using Salesforce" | select from companies where industry = "Software Development" and latest_funding_type = "Series B" and technographics.any(vendor = "Salesforce") | | "companies like Notion" | select from companies where products_and_services is_similar_to ("collaborative docs and knowledge management") | | "50 healthcare companies in Germany" | select from companies where industry = "Hospitals and Health Care" and locations.any(country_name = "Germany") limit 50 |

Response Behavior

• Summarize the result briefly (e.g. "Found 25 fintech companies in NYC").
• The tool returns a taskId for use with add-company-data-points, custom functions, or get-task-context.

Clay may render results in a widget in hosts that support MCP Apps, such as ChatGPT, claude.ai, and Cursor. Other terminal/coding-agent hosts such as Codex, Claude Code, Windsurf, and CLI environments do not show the widget. If you are unsure whether the widget is visible, assume it is not visible.

• If a widget is visible, avoid repeating the full widget contents unless the user asks for full contents; then call get-task-context with the taskId and answer inline.
• In terminal/coding-agent environments, when no widget is visible, or when the user asks for actual values/results, call get-task-context with the taskId and answer inline.
• NEVER tell the user that data was not found, not returned, or unavailable without first calling get-task-context. The initial search/tool response only includes base fields — enrichment results (emails, X/Twitter profiles, work history, custom data points, etc.) are only available via get-task-context.
• When the user asks about a specific value (e.g. "what's Patrick's email?", "what X profiles did you get?"), call get-task-context FIRST to check if the data has already been enriched — the user may have triggered enrichments through the widget. Only call add-contact-data-points / add-company-data-points if get-task-context shows the enrichment hasn't been run yet.
• Use get-task-context to poll until async results complete; if values are still in-progress, wait and retry rather than answering with missing values.
• If get-task-context is not available, fall back to get-task.

Displaying Results

This tool returns data only — it does NOT render a UI. Decide based on the user's END GOAL:

• Render when seeing the list is the goal (e.g. "find contacts at Ramp", "show me engineers at

Stripe", "who works at..."): call render-search-results with the returned taskId to show them in a widget. Several independent searches the user wants to see → render each.

• Do NOT render when the results feed something you'll do next — summarizing, comparing,

counting, ranking, filtering to answer, or feeding another tool/enrichment. Use the returned data (or get-task-context) directly. This TAKES PRECEDENCE: even if the request starts with "find" or "show me", if it continues into analysis (e.g. "...and summarize the commonalities"), the search is an intermediate step — skip rendering and answer from the data. You can render later if the user then asks to see the results.

Example: "Find SWEs at Clay, Ramp, and Google and summarize commonalities" → call the search tool three times, render none, answer from the returned data.

Enrichment

This tool does NOT enrich (it takes no data points). To add emails, work history, funding, tech stack, custom research, etc., call add-contact-data-points (for contacts) or add-company-data-points (for companies) with the returned taskId after this tool.

Search for contacts (people) by role, title, seniority, location, or employer, expressed as a Search DSL query. Searches PUBLICLY AVAILABLE people data — it is NOT the user's own CRM.

Quick Reference

• This tool: Find TYPES of people (e.g. "engineers at Stripe", "VPs of Sales at Ramp and Brex").
• search-contacts-by-name: Find SPECIFIC named people (e.g. "John Smith at Stripe").
• search-companies: Find LISTS of companies.
• query-objects + ask-question-about-accounts: the user's OWN accounts/deals/CRM.
• Follow-ups: ALWAYS re-call this tool with an updated query — never filter results in chat.

Parameters

companyIdentifiers (required)

One or more company domains or LinkedIn company URLs (up to 10). These companies are applied as a current-employer filter by the backend. Do NOT include clay.filter_to_companies(...) in dslQuery.

dslQuery (required)

A Search DSL query that MUST start with select from people. Include the requested person, role, seniority, location, and tenure filters; companyIdentifiers are attached separately by the backend.

Search DSL

Write a single Search DSL query. Grammar:

query    = "select" "from" entity where? limit_by? limit?
entity   = "people" | "companies"
where    = "where" predicate
limit_by = "limit" POSITIVE_INT "by" "clay_company_id"   (people only)
limit    = "limit" INTEGER

predicate = or_expr
or_expr   = and_expr ("or" and_expr)*
and_expr  = unary ("and" unary)*
unary     = "not" unary | comparison | aggregate | "(" predicate ")"

comparison = field op value | field "is_null" | field "is_not_null"
op    = "=" | "!=" | "<" | "<=" | ">" | ">=" | "contains" | "starts_with"
    | "ends_with" | "in" | "not_in" | "is_similar_to"
value = STRING | NUMBER | BOOLEAN | "(" value ("," value)* ")" | date_expr
date_expr = "today" "(" ")" (("+" | "-") "interval" POSITIVE_INT unit)?
unit  = "day[s]" | "week[s]" | "month[s]" | "year[s]"

Operators

• contains is whole-token match (not substring); list form: field contains ("a", "b").
• in / not_in take a value list; enum fields support only =, !=, in, not_in.
• is_similar_to expands meaning (e.g. job_title is_similar_to ("VP Sales")).
• and binds tighter than or; group with parentheses.

Limits

• Add limit N only when the user asks for a specific total count.
• limit N by clay_company_id (people queries only) caps results per company.

Company-scoped searches

• Pass every requested current employer through companyIdentifiers.
• Add role/seniority/tenure with experiences.any(is_current = true and ...).
• For a per-company cap ("N per company"), add limit N by clay_company_id.
• Filtering people by their employer's ATTRIBUTES (industry, size, funding) uses company.* inside

experiences.any(...) — this is an advanced cross-entity filter and may require a paid plan.

People fields (top-level in select from people)

• full_name (string): Full name of the person (first and last).
• location_city (string): City name, e.g. 'San Francisco', 'Berlin'. Common: "Aberdeen", "Abilene", "Akron", "Albany", "Albuquerque", "Alexandria", "Allentown", "Amarillo", "Anaheim", "Anchorage", "Ann Arbor", "Antioch", "Apple Valley", "Appleton", "Arlington", "Arvada", "Asheville", "Atlanta", "Atlantic City", "Augusta", …
• location_state (string): State, province, or municipality, e.g. 'California', 'Ontario'.
• location_country (string, enum): Full country name, e.g. 'United States', 'Germany'. Values: "Afghanistan", "Åland Islands", "Albania", "Algeria", "American Samoa", "Andorra", "Angola", "Anguilla", "Antarctica", "Antigua and Barbuda", "Argentina", "Armenia", "Aruba", "Australia", "Austria", "Azerbaijan", "Bahamas", "Bahrain", "Bangladesh", "Barbados", "Belarus", "Belgium", "Belize", "Benin", "Bermuda", "Bhutan", "Bolivia", "Bosnia and Herzegovina", "Botswana", "Bouvet Island", "Brazil", "British Indian Ocean Territory", "Brunei Darussalam", "Bulgaria", "Burkina Faso", "Burundi", "Cambodia", "Cameroon", "Canada", "Cape Verde", "Cayman Islands", "Central African Republic", "Chad", "Chile", "China", "Christmas Island", "Cocos (Keeling) Islands", "Collectivity of Saint Martin", "Colombia", "Comoros", "Cook Islands", "Costa Rica", "Côte d'Ivoire", "Croatia", "Cuba", "Curaçao", "Cyprus", "Czech Republic", "Democratic Republic of the Congo", "Denmark", "Djibouti", "Dominica", "Dominican Republic", "Ecuador", "Egypt", "El Salvador", "Equatorial Guinea", "Eritrea", "Estonia", "Ethiopia", "Falkland Islands (Malvinas)", "Faroe Islands", "Fiji", "Finland", "France", "French Guiana", "French Polynesia", "French Southern Territories", "Gabon", "Gambia", "Georgia", "Germany", "Ghana", "Gibralta", "Greece", "Greenland", "Grenada", "Guadeloupe", "Guam", "Guatemala", "Guernsey", "Guinea-Bissau", "Guinea", "Guyana", "Haiti", "Heard Island and McDonald Islands", "Holy See", "Honduras", "Hong Kong", "Hungary", "Iceland", "India", "Indonesia", "Iran", "Iraq", "Ireland", "Isle of Man", "Israel", "Italy", "Jamaica", "Japan", "Jersey", "Jordan", "Kazakhstan", "Kenya", "Kiribati", "Kuwait", "Kyrgyzstan", "Laos", "Latvia", "Lebanon", "Lesotho", "Liberia", "Libya", "Liechtenstein", "Lithuania", "Luxembourg", "Macao", "Madagascar", "Malawi", "Malaysia", "Maldives", "Mali", "Malta", "Marshall Islands", "Martinique", "Mauritania", "Mauritius", "Mayotte", "Mexico", "Micronesia", "Moldova", "Monaco", "Mongolia", "Montenegro", "Montserrat", "Morocco", "Mozambique", "Myanmar", "Namibia", "Nauru", "Nepal", "Netherlands", "New Caledonia", "New Zealand", "Nicaragua", "Niger", "Nigeria", "Niue", "Norfolk Island", "North Korea", "North Macedonia", "Northern Mariana Islands", "Norway", "Oman", "Pakistan", "Palau", "Palestine", "Panama", "Papua New Guinea", "Paraguay", "Peru", "Philippines", "Pitcairn", "Poland", "Portugal", "Puerto Rico", "Qatar", "Republic of the Congo", "Réunion", "Romania", "Russia", "Rwanda", "Saint Barthélemy", "Saint Helena, Ascension and Tristan da Cunha", "Saint Kitts and Nevis", "Saint Lucia", "Saint Pierre and Miquelon", "Saint Vincent and the Grenadines", "Samoa", "San Marino", "Sao Tome and Principe", "Saudi Arabia", "Senegal", "Serbia", "Seychelles", "Sierra Leone", "Singapore", "Sint Maarten", "Slovakia", "Slovenia", "Solomon Islands", "Somalia", "South Africa", "South Georgia and the South Sandwich Islands", "South Korea", "South Sudan", "Spain", "Sri Lanka", "Sudan", "Suriname", "Swaziland", "Sweden", "Switzerland", "Syria", "Taiwan", "Tajikistan", "Tanzania", "Thailand", "Timor-Leste", "Togo", "Tokelau", "Tonga", "Trinidad and Tobago", "Tunisia", "Turkey", "Turkmenistan", "Turks and Caicos Islands", "Tuvalu", "Uganda", "Ukraine", "United Arab Emirates", "United Kingdom", "United States Minor Outlying Islands", "United States", "Uruguay", "Uzbekistan", "Vanuatu", "Venezuela", "Vietnam", "Virgin Islands, British", "Virgin Islands, U.S.", "Wallis and Futuna", "Western Sahara", "Yemen", "Zambia", "Zimbabwe"
• location_region (string, enum): Geographic region. Values: "APAC", "EMEA", "LATAM", "NAM"
• estimated_follower_count (number): Estimated social media audience/follower count.
• network_size (number): Estimated professional network size (connection count).
• years_of_experience (number): Estimated full-time years of experience based on full-time roles on the profile.
• headline (string): Profile headline (the tagline below their name). Use contains for keyword matching.
• about (string): About/summary section of the profile. Use contains for keyword matching.
• languages (string, array): Languages listed on the profile. Use = for exact match, in for multiple. e.g. languages = "Spanish" or languages in ("Spanish", "French"). Common: "English", "Spanish", "French", "German", "Portuguese", "Chinese", "Japanese", "Hindi", "Arabic", "Korean", "Italian", "Dutch", "Russian"
• education (tuple array): Education history. Use .any() or .count() with inner predicates on subfields.

Subfields:

• school_name (string): Name of the school or university.
• degree (string): Degree obtained, e.g. 'Bachelor of Science', 'Master of Business Administration', 'PhD'.
• field_of_study (string): Academic major or field, e.g. 'Computer Science', 'Economics', 'Mechanical Engineering'.
• start_date (month): Date education started (YYYY-MM).
• end_date (month): Date education ended (YYYY-MM).
• description (string): Education description text. Use contains for keyword matching.
• activities_and_societies (string): Activities and societies during education. Use contains for keyword matching.

Experience fields (inside experiences.any(...))

• job_title (string): Job title of the experience. Common: "Academic Counselor", "Accountant", "Account Executive", "Accounting Analyst", "Accounting Clerk", "Accounting Manager", "Accounting Partner", "Accounting Supervisor", "Account Manager", "Account Representative", "Accounts Payable Clerk", "Accounts Payable Manager", "Accounts Receivable Clerk", "Accounts Receivable Manager", "Account Supervisor", "Activities Director", "Activities Worker", "Actor", "Actuary", "Acupuncturist", …
• description (string): Experience description text. Use contains for keyword matching.
• company_name (string): Company name for the experience.
• employment_type (string): Type of employment. Common: "Full-time", "Part-time", "Internship", "Self-employed", "Contract", "Permanent", "Freelance", "Volunteer", "Other", "Temporary", "Apprenticeship"
• seniority (string, enum): Seniority level of the role. Values: "Founder", "Owner", "Board Member" (Board member), "Partner", "C-suite", "VP", "Director", "Head", "Manager", "Senior", "Mid-level", "Entry", "Intern / In Training" (Intern / in training), "Unknown"
• is_current (boolean): True if this is the person's current role, false for past roles. In experiences.any(...) on people queries, omit is_current to match any tenure. In people.exists(...) / people.count(...) on companies queries, include is_current = true by default when the user doesn't specify between current vs past.
• start_date (month): Date the experience started (YYYY-MM).
• end_date (month): Date the experience ended (YYYY-MM). Empty if current role.
• location (string): Free-text location of the experience.
• location_city (string): City of the experience, e.g. 'San Francisco'. Common: "Aberdeen", "Abilene", "Akron", "Albany", "Albuquerque", "Alexandria", "Allentown", "Amarillo", "Anaheim", "Anchorage", "Ann Arbor", "Antioch", "Apple Valley", "Appleton", "Arlington", "Arvada", "Asheville", "Atlanta", "Atlantic City", "Augusta", …
• location_state (string): State or province of the experience, e.g. 'California'.
• location_country (string, enum): Country of the experience, e.g. 'United States'. Values: "Afghanistan", "Åland Islands", "Albania", "Algeria", "American Samoa", "Andorra", "Angola", "Anguilla", "Antarctica", "Antigua and Barbuda", "Argentina", "Armenia", "Aruba", "Australia", "Austria", "Azerbaijan", "Bahamas", "Bahrain", "Bangladesh", "Barbados", "Belarus", "Belgium", "Belize", "Benin", "Bermuda", "Bhutan", "Bolivia", "Bosnia and Herzegovina", "Botswana", "Bouvet Island", "Brazil", "British Indian Ocean Territory", "Brunei Darussalam", "Bulgaria", "Burkina Faso", "Burundi", "Cambodia", "Cameroon", "Canada", "Cape Verde", "Cayman Islands", "Central African Republic", "Chad", "Chile", "China", "Christmas Island", "Cocos (Keeling) Islands", "Collectivity of Saint Martin", "Colombia", "Comoros", "Cook Islands", "Costa Rica", "Côte d'Ivoire", "Croatia", "Cuba", "Curaçao", "Cyprus", "Czech Republic", "Democratic Republic of the Congo", "Denmark", "Djibouti", "Dominica", "Dominican Republic", "Ecuador", "Egypt", "El Salvador", "Equatorial Guinea", "Eritrea", "Estonia", "Ethiopia", "Falkland Islands (Malvinas)", "Faroe Islands", "Fiji", "Finland", "France", "French Guiana", "French Polynesia", "French Southern Territories", "Gabon", "Gambia", "Georgia", "Germany", "Ghana", "Gibralta", "Greece", "Greenland", "Grenada", "Guadeloupe", "Guam", "Guatemala", "Guernsey", "Guinea-Bissau", "Guinea", "Guyana", "Haiti", "Heard Island and McDonald Islands", "Holy See", "Honduras", "Hong Kong", "Hungary", "Iceland", "India", "Indonesia", "Iran", "Iraq", "Ireland", "Isle of Man", "Israel", "Italy", "Jamaica", "Japan", "Jersey", "Jordan", "Kazakhstan", "Kenya", "Kiribati", "Kuwait", "Kyrgyzstan", "Laos", "Latvia", "Lebanon", "Lesotho", "Liberia", "Libya", "Liechtenstein", "Lithuania", "Luxembourg", "Macao", "Madagascar", "Malawi", "Malaysia", "Maldives", "Mali", "Malta", "Marshall Islands", "Martinique", "Mauritania", "Mauritius", "Mayotte", "Mexico", "Micronesia", "Moldova", "Monaco", "Mongolia", "Montenegro", "Montserrat", "Morocco", "Mozambique", "Myanmar", "Namibia", "Nauru", "Nepal", "Netherlands", "New Caledonia", "New Zealand", "Nicaragua", "Niger", "Nigeria", "Niue", "Norfolk Island", "North Korea", "North Macedonia", "Northern Mariana Islands", "Norway", "Oman", "Pakistan", "Palau", "Palestine", "Panama", "Papua New Guinea", "Paraguay", "Peru", "Philippines", "Pitcairn", "Poland", "Portugal", "Puerto Rico", "Qatar", "Republic of the Congo", "Réunion", "Romania", "Russia", "Rwanda", "Saint Barthélemy", "Saint Helena, Ascension and Tristan da Cunha", "Saint Kitts and Nevis", "Saint Lucia", "Saint Pierre and Miquelon", "Saint Vincent and the Grenadines", "Samoa", "San Marino", "Sao Tome and Principe", "Saudi Arabia", "Senegal", "Serbia", "Seychelles", "Sierra Leone", "Singapore", "Sint Maarten", "Slovakia", "Slovenia", "Solomon Islands", "Somalia", "South Africa", "South Georgia and the South Sandwich Islands", "South Korea", "South Sudan", "Spain", "Sri Lanka", "Sudan", "Suriname", "Swaziland", "Sweden", "Switzerland", "Syria", "Taiwan", "Tajikistan", "Tanzania", "Thailand", "Timor-Leste", "Togo", "Tokelau", "Tonga", "Trinidad and Tobago", "Tunisia", "Turkey", "Turkmenistan", "Turks and Caicos Islands", "Tuvalu", "Uganda", "Ukraine", "United Arab Emirates", "United Kingdom", "United States Minor Outlying Islands", "United States", "Uruguay", "Uzbekistan", "Vanuatu", "Venezuela", "Vietnam", "Virgin Islands, British", "Virgin Islands, U.S.", "Wallis and Futuna", "Western Sahara", "Yemen", "Zambia", "Zimbabwe"
• location_region (string, enum): Geographic region of the experience. Values: "APAC", "EMEA", "LATAM", "NAM"

Employer fields (inside experiences.any(... company.* ...))

• domain (string): Company website domain, e.g. 'google.com', 'stripe.com'.
• description (string): Company description. Use contains for keyword matching.
• products_and_services (string): What the company does, makes, and sells, matched semantically against company document embeddings. Only supports is_similar_to with one or more non-empty string values; multiple values match companies similar to ANY value (e.g. products_and_services is_similar_to ("b2b saas", "crm")). Distinct from description keyword matching; not all companies have embeddings, and rows without one never match.
• company_type (string, enum): Company type classification. Values: "Privately Held" (Privately held), "Public Company" (Public company), "Partnership", "Self Employed" (Self-employed), "Non Profit" (Nonprofit), "Educational", "Self Owned" (Self-owned), "Government Agency" (Government agency)
• company_size (string, enum): Company size range bucket. Prefer this for first-pass company-size filtering; use estimated_employee_count only when the user explicitly asks for exact employee count/headcount. Values: "1" (1 employee), "2-10" (2–10 employees), "11-50" (11–50 employees), "51-200" (51–200 employees), "201-500" (201–500 employees), "501-1,000" (501–1,000 employees), "1,001-5,000" (1,001–5,000 employees), "5,001-10,000" (5,001–10,000 employees), "10,001+" (10,001+ employees)
• estimated_employee_count (number): Estimated total employee count. Use only when the user explicitly asks for exact employee count/headcount or asks to switch from company-size buckets to exact counts.
• estimated_follower_count (number): Estimated social media audience/follower count.
• year_founded (year): Year the company was founded.
• employee_growth_3mo (number): Employee growth ratio (1.1 = +10% growth, 0.9 = −10% decline).
• employee_growth_6mo (number): Employee growth ratio (1.1 = +10% growth, 0.9 = −10% decline).
• employee_growth_12mo (number): Employee growth ratio (1.1 = +10% growth, 0.9 = −10% decline).
• employee_growth_24mo (number): Employee growth ratio (1.1 = +10% growth, 0.9 = −10% decline).
• annual_revenue (string, enum): Annual revenue bracket. Use = or in with exact bucket values, not numeric operators. Values: "0-500K" ($0–$500K), "500K-1M" ($500K–$1M), "1M-5M" ($1M–$5M), "5M-10M" ($5M–$10M), "10M-25M" ($10M–$25M), "25M-75M" ($25M–$75M), "75M-200M" ($75M–$200M), "200M-500M" ($200M–$500M), "500M-1B" ($500M–$1B), "1B-10B" ($1B–$10B), "10B-100B" ($10B–$100B), "100B-1T" ($100B+)
• ai_business_types (string): Derived business model type. LOW COVERAGE — treat as optional: always pair with an is_null fallback, e.g. (ai_business_types contains "B2B" or ai_business_types is_null). Use contains for matching. Common: "B2B", "B2C", "Nonprofit"
• industry (string, enum): The company's main industry. This is the primary, structured way to filter companies by industry. Values: "Abrasives and Nonmetallic Minerals Manufacturing", "Accessible Architecture and Design", "Accommodation Services", "Accounting", "Administration of Justice", "Administrative and Support Services", "Advertising Services", "Agricultural Chemical Manufacturing", "Agriculture, Construction, Mining Machinery Manufacturing", "Air, Water, and Waste Program Management", "Airlines and Aviation", "Alternative Dispute Resolution", "Alternative Medicine", "Ambulance Services", "Amusement Parks and Arcades", "Animal Feed Manufacturing", "Animation", "Animation and Post-production", "Apparel Manufacturing", "Apparel and Fashion", "Appliances, Electrical, and Electronics Manufacturing", "Architectural and Structural Metal Manufacturing", "Architecture and Planning", "Armed Forces", "Artists and Writers", "Arts and Crafts", "Audio and Video Equipment Manufacturing", "Automation Machinery Manufacturing", "Automotive", "Aviation & Aerospace", "Aviation and Aerospace Component Manufacturing", "Baked Goods Manufacturing", "Banking", "Bars, Taverns, and Nightclubs", "Bed-and-Breakfasts, Hostels, Homestays", "Beverage Manufacturing", "Biomass Electric Power Generation", "Biotechnology", "Biotechnology Research", "Blockchain Services", "Blogs", "Boilers, Tanks, and Shipping Container Manufacturing", "Book Publishing", "Book and Periodical Publishing", "Breweries", "Broadcast Media Production and Distribution", "Building Construction", "Building Equipment Contractors", "Building Finishing Contractors", "Building Materials", "Building Structure and Exterior Contractors", "Business Consulting and Services", "Business Content", "Business Intelligence Platforms", "Business Supplies and Equipment", "Capital Markets", "Caterers", "Chemical Manufacturing", "Chemical Raw Materials Manufacturing", "Child Day Care Services", "Chiropractors", "Civic and Social Organizations", "Civil Engineering", "Claims Adjusting, Actuarial Services", "Clay and Refractory Products Manufacturing", "Climate Data and Analytics", "Climate Technology Product Manufacturing", "Coal Mining", "Collection Agencies", "Commercial Real Estate", "Commercial and Industrial Equipment Rental", "Commercial and Industrial Machinery Maintenance", "Commercial and Service Industry Machinery Manufacturing", "Communications Equipment Manufacturing", "Community Development and Urban Planning", "Community Services", "Computer Games", "Computer Hardware", "Computer Hardware Manufacturing", "Computer Networking", "Computer Networking Products", "Computer and Network Security", "Computers and Electronics Manufacturing", "Conservation Programs", "Construction", "Construction Hardware Manufacturing", "Consumer Electronics", "Consumer Goods", "Consumer Goods Rental", "Consumer Services", "Cosmetics", "Cosmetology and Barber Schools", "Courts of Law", "Credit Intermediation", "Dairy", "Dairy Product Manufacturing", "Dance Companies", "Data Infrastructure and Analytics", "Data Security Software Products", "Defense & Space", "Defense and Space Manufacturing", "Dentists", "Design", "Design Services", "Desktop Computing Software Products", "Digital Accessibility Services", "Distilleries", "E-Learning", "E-Learning Providers", "Economic Programs", "Education", "Education Administration Programs", "Education Management", "Electric Lighting Equipment Manufacturing", "Electric Power Generation", "Electric Power Transmission, Control, and Distribution", "Electrical Equipment Manufacturing", "Electronic and Precision Equipment Maintenance", "Embedded Software Products", "Emergency and Relief Services", "Engineering Services", "Engines and Power Transmission Equipment Manufacturing", "Entertainment", "Entertainment Providers", "Environmental Quality Programs", "Environmental Services", "Equipment Rental Services", "Events Services", "Executive Offices", "Executive Search Services", "Fabricated Metal Products", "Facilities Services", "Farming, Ranching, Forestry", "Farming", "Fashion Accessories Manufacturing", "Financial Services", "Fine Art", "Fine Arts Schools", "Fire Protection", "Fisheries", "Flight Training", "Food & Beverages", "Food and Beverage Manufacturing", "Food and Beverage Retail", "Food and Beverage Services", "Food Production", "Footwear Manufacturing", "Forestry and Logging", "Freight and Package Transportation", "Fruit and Vegetable Preserves Manufacturing", "Fundraising", "Funds and Trusts", "Furniture", "Furniture and Home Furnishings Manufacturing", "Gambling Facilities and Casinos", "Geothermal Electric Power Generation", "Glass Product Manufacturing", "Glass, Ceramics and Concrete Manufacturing", "Golf Courses and Country Clubs", "Government Administration", "Government Relations", "Government Relations Services", "Graphic Design", "Ground Passenger Transportation", "HVAC and Refrigeration Equipment Manufacturing", "Health and Human Services", "Health, Wellness and Fitness", "Higher Education", "Highway, Street, and Bridge Construction", "Historical Sites", "Holding Companies", "Home Health Care Services", "Horticulture", "Hospitality", "Hospitals", "Hospitals and Health Care", "Hotels and Motels", "Household Appliance Manufacturing", "Household Services", "Household and Institutional Furniture Manufacturing", "Housing Programs", "Housing and Community Development", "Human Resources", "Human Resources Services", "Hydroelectric Power Generation", "IT Services and IT Consulting", "IT System Custom Software Development", "IT System Data Services", "IT System Design Services", "IT System Installation and Disposal", "IT System Operations and Maintenance", "IT System Testing and Evaluation", "IT System Training and Support", "Import and Export", "Individual and Family Services", "Industrial Automation", "Industrial Machinery Manufacturing", "Industry Associations", "Information Services", "Information Technology and Services", "Insurance", "Insurance Agencies and Brokerages", "Insurance Carriers", "Insurance and Employee Benefit Funds", "Interior Design", "International Affairs", "International Trade and Development", "Internet Marketplace Platforms", "Internet News", "Internet Publishing", "Investment Advice", "Investment Banking", "Investment Management", "Janitorial Services", "Landscaping Services", "Language Schools", "Laundry and Drycleaning Services", "Law Enforcement", "Law Practice", "Leasing Non-residential Real Estate", "Leasing Residential Real Estate", "Leather Product Manufacturing", "Legal Services", "Legislative Offices", "Leisure, Travel & Tourism", "Libraries", "Loan Brokers", "Luxury Goods and Jewelry", "Machinery Manufacturing", "Manufacturing", "Maritime", "Maritime Transportation", "Market Research", "Marketing Services", "Mattress and Blinds Manufacturing", "Measuring and Control Instrument Manufacturing", "Meat Products Manufacturing", "Mechanical or Industrial Engineering", "Media & Telecommunications", "Media Production", "Medical Devices", "Medical Equipment Manufacturing", "Medical Practices", "Medical and Diagnostic Laboratories", "Mental Health Care", "Metal Ore Mining", "Metal Treatments", "Metal Valve, Ball, and Roller Manufacturing", "Metalworking Machinery Manufacturing", "Military and International Affairs", "Mining", "Mobile Computing Software Products", "Mobile Food Services", "Mobile Gaming Apps", "Motor Vehicle Manufacturing", "Motor Vehicle Parts Manufacturing", "Movies and Sound Recording", "Movies, Videos and Sound", "Museums", "Museums, Historical Sites, and Zoos", "Music", "Musicians", "Nanotechnology Research", "Natural Gas Distribution", "Newspaper Publishing", "Non-profit Organization Management", "Non-profit Organizations", "Nonmetallic Mineral Mining", "Nonresidential Building Construction", "Nuclear Electric Power Generation", "Nursing Homes and Residential Care Facilities", "Office Administration", "Office Furniture and Fixtures Manufacturing", "Oil and Gas", "Oil, Gas, and Mining", "Online Audio and Video Media", "Online Media", "Online and Mail Order Retail", "Operations Consulting", "Optometrists", "Outpatient Care Centers", "Outsourcing and Offshoring Consulting", "Outsourcing/Offshoring", "Packaging and Containers", "Packaging and Containers Manufacturing", "Paint, Coating, and Adhesive Manufacturing", "Paper and Forest Product Manufacturing", "Paper and Forest Products", "Performing Arts", "Performing Arts and Spectator Sports", "Periodical Publishing", "Personal Care Product Manufacturing", "Personal Care Services", "Personal and Laundry Services", "Pet Services", "Pharmaceutical Manufacturing", "Philanthropic Fundraising Services", "Philanthropy", "Photography", "Physical, Occupational and Speech Therapists", "Physicians", "Plastics Manufacturing", "Plastics and Rubber Product Manufacturing", "Political Organizations", "Primary Metal Manufacturing", "Primary and Secondary Education", "Printing Services", "Professional Organizations", "Professional Services", "Professional Training and Coaching", "Program Development", "Public Assistance Programs", "Public Health", "Public Policy", "Public Policy Offices", "Public Relations and Communications Services", "Public Safety", "Radio and Television Broadcasting", "Rail Transportation", "Railroad Equipment Manufacturing", "Ranching", "Real Estate", "Real Estate Agents and Brokers", "Real Estate and Equipment Rental Services", "Recreational Facilities", "Religious Institutions", "Renewable Energy Equipment Manufacturing", "Renewable Energy Power Generation", "Renewable Energy Semiconductor Manufacturing", "Renewables & Environment", "Repair and Maintenance", "Research", "Research Services", "Residential Building Construction", "Restaurants", "Retail", "Retail Apparel and Fashion", "Retail Appliances, Electrical, and Electronic Equipment", "Retail Art Dealers", "Retail Art Supplies", "Retail Books and Printed News", "Retail Building Materials and Garden Equipment", "Retail Florists", "Retail Furniture and Home Furnishings", "Retail Gasoline", "Retail Groceries", "Retail Health and Personal Care Products", "Retail Luxury Goods and Jewelry", "Retail Motor Vehicles", "Retail Musical Instruments", "Retail Office Equipment", "Retail Office Supplies and Gifts", "Retail Pharmacies", "Retail Recyclable Materials & Used Merchandise", "Reupholstery and Furniture Repair", "Robotics Engineering", "Rubber Products Manufacturing", "Satellite Telecommunications", "School and Employee Bus Services", "Seafood Product Manufacturing", "Securities and Commodity Exchanges", "Security Guards and Patrol Services", "Security Systems Services", "Security and Investigations", "Semiconductor Manufacturing", "Semiconductors", "Services for Renewable Energy", "Services for the Elderly and Disabled", "Sheet Music Publishing", "Shipbuilding", "Shuttles and Special Needs Transportation Services", "Sightseeing Transportation", "Soap and Cleaning Product Manufacturing", "Social Networking Platforms", "Software Development", "Solar Electric Power Generation", "Sound Recording", "Space Research and Technology", "Specialty Trade Contractors", "Spectator Sports", "Sporting Goods", "Sporting Goods Manufacturing", "Sports Teams and Clubs", "Sports and Recreation Instruction", "Spring and Wire Product Manufacturing", "Staffing and Recruiting", "Steam and Air-Conditioning Supply", "Strategic Management Services", "Subdivision of Land", "Sugar and Confectionery Product Manufacturing", "Surveying and Mapping Services", "Taxi and Limousine Services", "Technical and Vocational Training", "Technology, Information and Internet", "Technology, Information and Media", "Telecommunications", "Telecommunications Carriers", "Telephone Call Centers", "Temporary Help Services", "Textile Manufacturing", "Theater Companies", "Think Tanks", "Tobacco", "Tobacco Manufacturing", "Translation and Localization", "Transportation Equipment Manufacturing", "Transportation Programs", "Transportation, Logistics, Supply Chain and Storage", "Transportation/Trucking/Railroad", "Travel Arrangements", "Truck Transportation", "Trusts and Estates", "Turned Products and Fastener Manufacturing", "Urban Transit Services", "Utilities", "Utilities Administration", "Utility System Construction", "Vehicle Repair and Maintenance", "Venture Capital and Private Equity Principals", "Veterinary", "Veterinary Services", "Vocational Rehabilitation Services", "Warehousing", "Warehousing and Storage", "Waste Collection", "Waste Treatment and Disposal", "Water Supply and Irrigation Systems", "Water, Waste, Steam, and Air Conditioning Services", "Wellness and Fitness Services", "Wholesale", "Wholesale Alcoholic Beverages", "Wholesale Apparel and Sewing Supplies", "Wholesale Appliances, Electrical, and Electronics", "Wholesale Building Materials", "Wholesale Chemical and Allied Products", "Wholesale Computer Equipment", "Wholesale Drugs and Sundries", "Wholesale Food and Beverage", "Wholesale Footwear", "Wholesale Furniture and Home Furnishings", "Wholesale Hardware, Plumbing, Heating Equipment", "Wholesale Import and Export", "Wholesale Luxury Goods and Jewelry", "Wholesale Machinery", "Wholesale Metals and Minerals", "Wholesale Motor Vehicles and Parts", "Wholesale Paper Products", "Wholesale Petroleum and Petroleum Products", "Wholesale Raw Farm Products", "Wholesale Recyclable Materials", "Wind Electric Power Generation", "Wine and Spirits", "Wineries", "Wireless Services", "Wood Product Manufacturing", "Writing and Editing", "Zoos and Botanical Gardens"
• naics_codes_2022 (string, enum, array): NAICS 2022 industry classification codes as numeric strings (2-6 digits). Matching is hierarchical: a code matches companies whose more specific codes fall under it (e.g. "5132" matches a company classified "513210"). Census publishes three 2-digit sectors as ranges: "31-33" (Manufacturing), "44-45" (Retail Trade), "48-49" (Transportation and Warehousing). Use = for one code, in for multiple, e.g. naics_codes_2022 in ("31-33", "541511"). Values: "11" (11: Agriculture, Forestry, Fishing and Hunting), "111" (111: Crop Production), "1111" (1111: Oilseed and Grain Farming), "11111" (11111: Soybean Farming), "111110" (111110: Soybean Farming), "11112" (11112: Oilseed (except Soybean) Farming), "111120" (111120: Oilseed (except Soybean) Farming), "11113" (11113: Dry Pea and Bean Farming), "111130" (111130: Dry Pea and Bean Farming), "11114" (11114: Wheat Farming), "111140" (111140: Wheat Farming), "11115" (11115: Corn Farming), "111150" (111150: Corn Farming), "11116" (11116: Rice Farming), "111160" (111160: Rice Farming), "11119" (11119: Other Grain Farming), "111191" (111191: Oilseed and Grain Combination Farming), "111199" (111199: All Other Grain Farming), "1112" (1112: Vegetable and Melon Farming), "11121" (11121: Vegetable and Melon Farming), …
• ai_industries (string, enum, array): AI-derived industry classification. Do NOT filter on this field unless the user explicitly asks for ai_industries — default vertical filtering uses industry. Use = for exact match, in for multiple. e.g. ai_industries = "Professional, Business and Legal Services". Values: "Agriculture, Forestry and Fisheries", "Automotive, Aerospace and Defense Manufacturing", "Education and Training", "Energy, Utilities and Environmental Services", "Finance and Insurance", "Healthcare and Life Sciences", "Hospitality, Food and Travel Services", "Industrial Manufacturing and Materials", "Media, Entertainment and Culture", "Non-Profit, Public Sector and Education (Non-Commercial)", "Personal and Home Services", "Professional, Business and Legal Services", "Real Estate and Construction", "Retail and Consumer Channels", "Software and IT", "Transportation and Logistics"
• ai_subindustries (string, enum, array): AI-derived subindustry classification. Use = for exact match, in for multiple. e.g. ai_subindustries = "AI and ML Platforms". Values: "AI and ML Platforms", "Agriculture and Forestry Software", "Blockchain and Web3", "Carriers and ISPs", "Cloud and Infrastructure Software", "Consumer Software", "Data and Analytics Software", "Developer Tools and Platforms", "Enterprise Software Solutions", "Financial Services Software", "Government and Public Sector Software", "Hardware and Networking", "Healthcare Software", "IoT and Embedded Systems Software", "IT Services and Cybersecurity", "Manufacturing Software", "Metaverse, AR/VR and Other Emerging Platforms", "Quantum Computing Software", "Real Estate and PropTech Software", "Retail and Ecommerce Software", "Security and Identity Software", "Biotechnology and Pharmaceuticals", "Digital Health and Telemedicine", "Hospitals, Clinics and Outpatient Care", "Medical Devices and Diagnostic Equipment", "Medical Testing and Clinical Laboratories", "Mental Health and Rehabilitation Services", "Pharma Distribution and CRO Services", "Banking and Lending", "Capital Markets and Cryptocurrency", "Cryptocurrency and Blockchain Services", "Financial Services Platforms", "Insurance and InsurTech", "Investment Management and WealthTech", "Venture Capital and Private Equity", "Electric Power and Grid Management", "Nuclear and Advanced Generation", "Oil and Gas Exploration, Production and Services", "Renewable Energy and Clean Tech", "Sustainability Tech and Environmental Consulting", "Water, Waste and Environmental Management", "3D Printing and Advanced Manufacturing", "Building Materials and Chemicals", "Consumer Goods and Appliances", "Electronics and Computer Equipment", "Food, Beverage and Tobacco Production", "Industrial Machinery and Equipment", "Mining, Metals and Natural Resources", "Architecture, Urban Planning and Green Building", "Commercial Real Estate Development and Leasing", "Construction and Civil Engineering Services", "Property and Facility Management", "Residential Real Estate Development and Brokerage", "Specialty Construction Products", "Automotive Service and Collision Repair", "Brick-and-Mortar Retail", "Media and Entertainment Retail", "Online Commerce and Marketplaces", "Retail Technology", "Specialty Auctions and Collectibles", "Wholesale and Distribution", "Autonomous Vehicles and Drone Delivery", "Car and Truck Rental", "Freight and Cargo", "Logistics Technology", "Passenger Transit and Mobility", "Warehousing, Fulfillment and 3PL Services", "Accounting, Audit and Financial Advisory", "Advertising, Marketing and Multimedia Design", "Defense and Government Services", "Facilities Management and Commercial Cleaning", "Human Resources, Staffing and Recruitment", "Legal Services and Regulatory Compliance", "Management Consulting and Strategy Consulting", "Translation, Document and Information Management", "Corporate Training and Learning and Development", "E-Learning Platforms and EdTech", "K-12 and Higher Education Institutions", "Test Prep, Tutoring and After-School Services", "Vocational Training and Certification Programs", "Digital Publishing and Streaming Platforms", "Film, Television and Broadcasting", "Gaming, Esports and Interactive Entertainment", "Live Events, Experiences and Ticketed Attractions", "Museums, Art Galleries and Cultural Preservation", "Music, Audio and Podcast Services", "Sports and Recreation", "Food and Beverage Services", "Hospitality and Lodging", "Travel Agencies and Leisure Services", "Funeral Homes and Related Services", "Home Services", "Personal Care and Wellness", "Veterinary Care and Pet Services", "AgriTech and Precision Farming", "Aquaculture and Fisheries", "Crop Farming and Livestock Production", "Farming Equipment and Supplies", "Forestry, Logging and Wood Products", "Mining and Extraction", "Aviation and Aerospace Component Manufacturing", "Automotive and Rental Retail", "Commercial Space Innovation", "Defense Systems and Marine Manufacturing", "Motor Vehicle and Parts Manufacturing", "Government Administration and Municipal Services", "NGOs, Charities and Community Organizations", "Public Healthcare and Social Services", "Public/Private Research Institutions and Educational Foundations", "Student Organizations and Campus Services"
• ai_revenue_streams (string, enum, array): AI-derived revenue stream classification. Do NOT filter on this field unless the user explicitly asks for revenue streams. Use = for exact match, in for multiple. e.g. ai_revenue_streams = "SaaS". Values: "Professional Services", "Financial Services", "Subscriptions/Recurring", "Product Sales", "Transaction Fees", "Rental/Leasing", "Project/Contract Work", "Event/Experience Revenue", "Grants/Donations", "Licensing/IP", "Advertising"
• locations (tuple array): All office locations. Use .any() or .count() with inner predicates on subfields.

Subfields:

• country_name (string, enum): Full country name, e.g. 'United States', 'Germany'. Values: "Afghanistan", "Albania", "Algeria", "Andorra", "Angola", "Anguilla", "Antarctica", "Antigua and Barbuda", "Argentina", "Armenia", "Aruba", "Australia", "Austria", "Azerbaijan", "Bahamas", "Bahrain", "Bangladesh", "Barbados", "Belarus", "Belgium", "Belize", "Benin", "Bermuda", "Bhutan", "Bolivia", "Bonaire, Saint Eustatius and Saba ", "Bosnia and Herzegovina", "Botswana", "Brazil", "British Virgin Islands", "Brunei", "Bulgaria", "Burkina Faso", "Burundi", "Cambodia", "Cameroon", "Canada", "Cape Verde", "Cayman Islands", "Central African Republic", "Chad", "Chile", "China", "Colombia", "Comoros", "Costa Rica", "Croatia", "Cuba", "Curacao", "Cyprus", "Czechia", "Democratic Republic of the Congo", "Denmark", "Djibouti", "Dominican Republic", "East Timor", "Ecuador", "Egypt", "El Salvador", "Equatorial Guinea", "Estonia", "Ethiopia", "Faroe Islands", "Fiji", "Finland", "France", "French Guiana", "French Polynesia", "Gabon", "Gambia", "Georgia", "Germany", "Ghana", "Gibraltar", "Greece", "Greenland", "Grenada", "Guadeloupe", "Guam", "Guatemala", "Guernsey", "Guinea", "Guyana", "Haiti", "Honduras", "Hong Kong", "Hungary", "Iceland", "India", "Indonesia", "Iran", "Iraq", "Ireland", "Isle of Man", "Israel", "Italy", "Ivory Coast", "Jamaica", "Japan", "Jersey", "Jordan", "Kazakhstan", "Kenya", "Kosovo", "Kuwait", "Kyrgyzstan", "Laos", "Latvia", "Lebanon", "Lesotho", "Liberia", "Libya", "Liechtenstein", "Lithuania", "Luxembourg", "Macao", "Macedonia", "Madagascar", "Malawi", "Malaysia", "Maldives", "Mali", "Malta", "Marshall Islands", "Martinique", "Mauritania", "Mauritius", "Mayotte", "Mexico", "Moldova", "Monaco", "Mongolia", "Montenegro", "Morocco", "Mozambique", "Myanmar", "Namibia", "Nepal", "Netherlands", "Netherlands Antilles", "New Caledonia", "New Zealand", "Nicaragua", "Niger", "Nigeria", "North Korea", "Northern Mariana Islands", "Norway", "Oman", "Pakistan", "Palestinian Territory", "Panama", "Papua New Guinea", "Paraguay", "Peru", "Philippines", "Poland", "Portugal", "Puerto Rico", "Qatar", "Republic of the Congo", "Reunion", "Romania", "Russia", "Rwanda", "Saint Barthelemy", "Saint Kitts and Nevis", "Saint Lucia", "Saint Vincent and the Grenadines", "Samoa", "San Marino", "Sao Tome and Principe", "Saudi Arabia", "Senegal", "Serbia", "Serbia and Montenegro", "Seychelles", "Sierra Leone", "Singapore", "Sint Maarten", "Slovakia", "Slovenia", "Somalia", "South Africa", "South Korea", "South Sudan", "Spain", "Sri Lanka", "Sudan", "Suriname", "Svalbard and Jan Mayen", "Swaziland", "Sweden", "Switzerland", "Syria", "Taiwan", "Tajikistan", "Tanzania", "Thailand", "Togo", "Tonga", "Trinidad and Tobago", "Tunisia", "Turkey", "Turkmenistan", "Turks and Caicos Islands", "U.S. Virgin Islands", "Uganda", "Ukraine", "United Arab Emirates", "United Kingdom", "United States", "Uruguay", "Uzbekistan", "Vanuatu", "Venezuela", "Vietnam", "Yemen", "Zambia", "Zimbabwe"
• city (string): City name, e.g. 'San Francisco', 'Berlin'. Common: "Aberdeen", "Abilene", "Akron", "Albany", "Albuquerque", "Alexandria", "Allentown", "Amarillo", "Anaheim", "Anchorage", "Ann Arbor", "Antioch", "Apple Valley", "Appleton", "Arlington", "Arvada", "Asheville", "Atlanta", "Atlantic City", "Augusta", …
• state_or_province (string): State, province, or first-level administrative district, e.g. 'California', 'Ontario'.
• postal_code (string): Postal or ZIP code, e.g. '94107'.
• region (string, enum): Business region for the office location. Values: "APAC", "EMEA", "LATAM", "NAM"
• is_headquarters (boolean): True when this location is the company headquarters (primary office).
• technographics (tuple array): Technology stack installed at the company, backed by BuyerCaddy data. Use .any() or .count() with inner predicates on subfields.

Subfields:

• vendor (string): Technology vendor name. Common: "Microsoft", "Google", "Amazon", "Adobe", "Oracle", "The PHP Group", "Facebook, Inc.", "Automattic Inc.", "Cloudflare", "Apache", "Meta Platforms, Inc"
• product (string): Product name. Common: "Amazon Web Services (AWS)", "Amazon Web Hosting", "Google Analytics 360", "PHP", "Google Tag Manager", "Microsoft 365 Apps & Services", "Google Marketing Platform", "Amazon EC2", "Microsoft Exchange", "GoDaddy Hosting"
• product_category (string): Top-level product category. Common: "IT Infrastructure", "Collaboration & Productivity", "Marketing", "Development", "Content Management", "Digital Advertising Tech", "Hosting", "CI/CD Tools", "Cloud Data Integration", "Web Hosting"

Examples

| User says | companyIdentifiers | dslQuery | |-----------|--------------------|----------| | "engineers at Stripe" | ["stripe.com"] | select from people where experiences.any(is_current = true and job_title is_similar_to ("engineer")) | | "up to 5 VPs of Sales at Stripe, Ramp, and Brex" | ["stripe.com", "ramp.com", "brex.com"] | select from people where experiences.any(is_current = true and job_title is_similar_to ("VP Sales")) limit 5 by clay_company_id | | "new hires at Stripe in the last 3 months" | ["stripe.com"] | select from people where experiences.any(is_current = true and start_date >= today() - interval 3 months) |

Handling Follow-ups

ANY change to the search requires re-calling this tool with a modified query — never filter in chat.

• "also / too" → add predicates with and, keeping prior filters.
• "only / just" → narrow the relevant predicate.
• "instead / actually" → replace the relevant predicate.
• When ambiguous, ask the user.

Response Behavior

• Summarize the search briefly (e.g., "Found 20 engineers at OpenAI").
• The tool returns a taskId for use with add-contact-data-points, add-company-data-points, custom functions, or get-task-context.
• For emails, use add-contact-data-points with the taskId.

Clay may render results in a widget in hosts that support MCP Apps, such as ChatGPT, claude.ai, and Cursor. Other terminal/coding-agent hosts such as Codex, Claude Code, Windsurf, and CLI environments do not show the widget. If you are unsure whether the widget is visible, assume it is not visible.

• If a widget is visible, avoid repeating the full widget contents unless the user asks for full contents; then call get-task-context with the taskId and answer inline.
• In terminal/coding-agent environments, when no widget is visible, or when the user asks for actual values/results, call get-task-context with the taskId and answer inline.
• NEVER tell the user that data was not found, not returned, or unavailable without first calling get-task-context. The initial search/tool response only includes base fields — enrichment results (emails, X/Twitter profiles, work history, custom data points, etc.) are only available via get-task-context.
• When the user asks about a specific value (e.g. "what's Patrick's email?", "what X profiles did you get?"), call get-task-context FIRST to check if the data has already been enriched — the user may have triggered enrichments through the widget. Only call add-contact-data-points / add-company-data-points if get-task-context shows the enrichment hasn't been run yet.
• Use get-task-context to poll until async results complete; if values are still in-progress, wait and retry rather than answering with missing values.
• If get-task-context is not available, fall back to get-task.

Zero Results

Suggest broadening: relax role terms (is_similar_to already expands), drop location or tenure, or verify the companyIdentifiers.

Displaying Results

This tool returns data only — it does NOT render a UI. Decide based on the user's END GOAL:

• Render when seeing the list is the goal (e.g. "find contacts at Ramp", "show me engineers at

Stripe", "who works at..."): call render-search-results with the returned taskId to show them in a widget. Several independent searches the user wants to see → render each.

• Do NOT render when the results feed something you'll do next — summarizing, comparing,

counting, ranking, filtering to answer, or feeding another tool/enrichment. Use the returned data (or get-task-context) directly. This TAKES PRECEDENCE: even if the request starts with "find" or "show me", if it continues into analysis (e.g. "...and summarize the commonalities"), the search is an intermediate step — skip rendering and answer from the data. You can render later if the user then asks to see the results.

Example: "Find SWEs at Clay, Ramp, and Google and summarize commonalities" → call the search tool three times, render none, answer from the returned data.

Enrichment

This tool does NOT enrich (it takes no data points). To add emails, work history, funding, tech stack, custom research, etc., call add-contact-data-points (for contacts) or add-company-data-points (for companies) with the returned taskId after this tool.

Find and enrich specific named contacts at their companies.

Quick Reference

• This tool: Find SPECIFIC named people (e.g., "John Smith at OpenAI", "Jane Doe at Stripe")
• search-contacts: Find TYPES of people (e.g., "engineers at Stripe")
• Do NOT use if user only provides company names without contact names
• Do NOT use to enrich contacts already in an existing search — use add-contact-data-points with entityIds instead

Parameters

contacts (required)

Array of { contactName, companyIdentifier } objects.

• contactName: First name, last name, or full name (e.g., "John", "Smith", or "John Smith")
• companyIdentifier: Domain or company LinkedIn URL (NOT person LinkedIn URLs)
• Domains: "openai.com", "stripe.com"
• LinkedIn: "linkedin.com/company/openai"
• Company names: Convert if confident (e.g., "Stripe" → "stripe.com"), otherwise ask user

Examples

| User request | contacts | |--------------|----------| | "Find John Smith at OpenAI" | [{ contactName: "John Smith", companyIdentifier: "openai.com" }] | | "Look up Jane Doe at Stripe and Bob Lee at Figma" | [{ contactName: "Jane Doe", companyIdentifier: "stripe.com" }, { contactName: "Bob Lee", companyIdentifier: "figma.com" }] |

Follow-ups

• "Add [name] at [company] too" → Re-call with ALL contacts (previous + new)
• "Actually look up [different people]" → Re-call with only the new contacts

Response Behavior

• Summarize the search briefly (e.g., "Found 20 engineers at OpenAI").
• The tool returns a taskId for use with add-contact-data-points, add-company-data-points, custom functions, or get-task-context.
• For emails, use add-contact-data-points with the taskId.

Clay may render results in a widget in hosts that support MCP Apps, such as ChatGPT, claude.ai, and Cursor. Other terminal/coding-agent hosts such as Codex, Claude Code, Windsurf, and CLI environments do not show the widget. If you are unsure whether the widget is visible, assume it is not visible.

• If a widget is visible, avoid repeating the full widget contents unless the user asks for full contents; then call get-task-context with the taskId and answer inline.
• In terminal/coding-agent environments, when no widget is visible, or when the user asks for actual values/results, call get-task-context with the taskId and answer inline.
• NEVER tell the user that data was not found, not returned, or unavailable without first calling get-task-context. The initial search/tool response only includes base fields — enrichment results (emails, X/Twitter profiles, work history, custom data points, etc.) are only available via get-task-context.
• When the user asks about a specific value (e.g. "what's Patrick's email?", "what X profiles did you get?"), call get-task-context FIRST to check if the data has already been enriched — the user may have triggered enrichments through the widget. Only call add-contact-data-points / add-company-data-points if get-task-context shows the enrichment hasn't been run yet.
• Use get-task-context to poll until async results complete; if values are still in-progress, wait and retry rather than answering with missing values.
• If get-task-context is not available, fall back to get-task.
• When Clay Audiences is enabled for the workspace, each result may include existsInAudiences — whether that record already exists in the user's Audiences (their system of record) — and, for matches, audienceEntityId plus audienceFields (the existing record's current field values, keyed by display name). Use this to tell net-new prospects apart from records the user already has, and answer questions about a matched record's existing data directly from audienceFields without extra tool calls; company audienceEntityId values can be passed to ask-question-about-accounts for deeper analysis. When existsInAudiences is absent, membership is unknown — do NOT claim a record is or isn't in Audiences.

Displaying Results

This tool returns data only — it does NOT render a UI. Decide based on the user's END GOAL:

• Render when seeing the list is the goal (e.g. "find contacts at Ramp", "show me engineers at

Stripe", "who works at..."): call render-search-results with the returned taskId to show them in a widget. Several independent searches the user wants to see → render each.

• Do NOT render when the results feed something you'll do next — summarizing, comparing,

counting, ranking, filtering to answer, or feeding another tool/enrichment. Use the returned data (or get-task-context) directly. This TAKES PRECEDENCE: even if the request starts with "find" or "show me", if it continues into analysis (e.g. "...and summarize the commonalities"), the search is an intermediate step — skip rendering and answer from the data. You can render later if the user then asks to see the results.

Example: "Find SWEs at Clay, Ramp, and Google and summarize commonalities" → call the search tool three times, render none, answer from the returned data.

Enrichment

This tool does NOT enrich (it takes no data points). To add emails, work history, funding, tech stack, custom research, etc., call add-contact-data-points (for contacts) or add-company-data-points (for companies) with the returned taskId after this tool.

Track an analytics event with optional properties.