enrich_company
ChatGPTEnrich a single company with full data from public sources (description, industry, headquarters, employee count, funding, offices, etc.).
Business & Operations
Overview
Power your sales or recruiting workflows directly in ChatGPT with live B2B data. DataForB2B lets you search people and companies using 70+ filters including job title, skills, company size, LinkedIn, funding stage, investor, past employers, certifications, years of experience, GitHub repositories, languages and more. Enrich any profile with verified work emails and GitHub profiles. Data sourced live across 60+ public sources. GDPR and CCPA compliant.
Tools
enrich_profile
ChatGPTEnrich a single professional profile with detailed profile data, work email, personal email, and/or GitHub profile. Each enrichment flag controls one data source and bills separately. To enrich SEVERAL profiles, use
enrich_profiles (bulk) instead — it runs them concurrently server-side and is far faster than calling this in a loop.enrich_profiles
ChatGPTEnrich MULTIPLE professional profiles in one call (1-100 at a time). The profiles are enriched concurrently server-side, so this is much faster and a single round-trip instead of calling enrich_profile in a loop. Use this whenever you have more than one profile to enrich (e.g. a list of people from search_people). Each enrichment flag controls one data source and bills separately, per SUCCESSFUL profile — a profile that fails comes back with an
error field and costs nothing. Returns results: one object per input identifier, each with the requested fields (profile, work_email, personal_email, phone, git_profile) or an error.search_company
ChatGPTSearch companies using structured filters. Use this for any company search: translate the user's intent (e.g. "AI startups in France that raised Series A") into structured filters on specific columns (industry, country, employee count range, funding stage, founded year, etc.). Returns paginated companies matching ALL/ANY filter conditions depending on the
op of the FilterGroup. Call this tool directly to search. If a categorical filter returns no results, the typeahead tool can resolve the exact stored value (see the per-column markers below). Available columns for filters.conditions[].column. Some free-text categorical columns are marked (typeahead: TYPE). Filter on them directly with the value the user gave. Don't hesitate to use the typeahead tool with that TYPE to resolve the exact stored value when the query is complex, when you're unsure the value or column matches the user's intent, or when a search returns few/no results — then retry. BASIC INFO - name (=, like, in) — company name, e.g. "Google", "Microsoft" (typeahead: company) - tagline (=, like) — company tagline / slogan - description (=, like) — company description - domain (=, like, in) — domain name (e.g. "google.com", "microsoft.com") - universal_name (=, like, in) — universal slug identifier (e.g. "google", "microsoft") - keyword (like) — full-text search in name / tagline / description - industry (=, like, in) — industry, lowercase (e.g. "software development", "it services and it consulting", "financial services", "business consulting and services", "advertising services", "hospitals and health care") (typeahead: company_industry) SIZE - employee_count (=, >, >=, <, <=, between, in) — number of employees (int) or range: "1-10", "11-50", "51-200", "201-500", "501-1000", "1001-5000", "5001-10000", "10001+" HEADQUARTERS - country_iso_code (=, in) — ISO-2 country code (e.g. "US", "FR", "GB", "DE", "CA") - city (=, like, in) — city name, e.g. "Paris", "San Francisco", "London" (typeahead: city) - region (=, like, in) — region / state, e.g. "California", "Île-de-France", "New York" (typeahead: region) OFFICES - office_country (=, in) — office ISO-2 country code - office_city (=, like, in) — office city name (typeahead: city) - office_region (=, like, in) — office region / state (typeahead: region) GROWTH - employee_growth_1m (=, >, >=, <, <=, between) — employee growth % over last 1 month - employee_growth_6m (=, >, >=, <, <=, between) — employee growth % over last 6 months - employee_growth_12m (=, >, >=, <, <=, between) — employee growth % over last 12 months - recent_hires_count (=, >, >=, <, <=, between) — number of recent hires METADATA - founded_year (=, >, >=, <, <=, between) — year founded (e.g. 1998, 2010, 2020) - company_type (=, in) — UPPERCASE snake_case: "PRIVATELY_HELD", "PUBLIC_COMPANY", "NON_PROFIT", "PARTNERSHIP", "SELF_OWNED", "EDUCATIONAL", "SELF_EMPLOYED", "GOVERNMENT_AGENCY" - follower_count (=, >, >=, <, <=, between) — number of followers - page_verified (=) — bool, whether the company profile is verified - category (=, like, in) — company category, lowercase (e.g. "software", "consulting", "financial services", "e-commerce", "health care", "manufacturing", "marketing", "advertising") (typeahead: category) FUNDING - last_funding_amount_usd (=, >, >=, <, <=, between) — last funding round amount in USD - last_funding_date (=, >, >=, <, <=) — last funding round date (e.g. "2023-06-15") - funding_stage_normalized (=, like, in) — current funding stage. Values: seed_round, series_a, series_b, series_c, series_d, series_e, series_f, series_g, series_h, series_unknown, pre_seed_round, angel_round, grant, private_equity_round, debt_financing, convertible_note, corporate_round, equity_crowdfunding, post_ipo_equity, post_ipo_debt, post_ipo_secondary, secondary_market, non_equity_assistance, product_crowdfunding, initial_coin_offering, undisclosed - has_funding (=) — bool, whether the company has raised funding Operators: =, >, >=, <, <=, between (requires value and value2), in (value is a list), like (text search, case-inse…search_lookalike
ChatGPTFind similar people or companies using AI-powered vector similarity. Provide either
profile (to find similar people) OR company (to find similar companies) — not both. Optionally narrow results with country or location.search_people
ChatGPTSearch professional profiles using structured filters. Use this for any people search: translate the user's intent (e.g. "AI engineers in Berlin who recently raised") into structured filters on specific columns (country, company size range, funding stage, etc.). Returns paginated profiles matching ALL/ANY filter conditions depending on the
op of the FilterGroup. To find people at a SPECIFIC company you already identified (e.g. via search_company or enrich_company), filter on current_company_id (or past_company_id) with that company's id (e.g. "org_xxx") — NOT current_company (the name), which also matches other companies that happen to share the name and adds noise. Call this tool directly to search. If a categorical filter returns no results, the typeahead tool can resolve the exact stored value (see the per-column markers below). Available columns for filters.conditions[].column. Some free-text categorical columns are marked (typeahead: TYPE). Filter on them directly with the value the user gave. Don't hesitate to use the typeahead tool with that TYPE to resolve the exact stored value when the query is complex, when you're unsure the value or column matches the user's intent, or when a search returns few/no results — then retry. PROFILE - first_name (=, like, in) — person's first name - last_name (=, like, in) — person's last name - profile_location (=, like) — current location, city/state (typeahead: location) - profile_country (=, in) — ISO-2 country code, UPPERCASE (e.g. "US", "GB", "FR", "DE", "CA"). Use GB (not UK) for the United Kingdom - profile_industry (=, like, in) — profile industry (typeahead: people_industry) - follower_count (=, >, >=, <, <=, between) — number of profile followers - keyword (like) — full-text search in headline (trigram matching) CURRENT JOB - current_company (=, like, in) — current employer NAME. Name matching is fuzzy: it also matches OTHER, unrelated companies that share the same name. Only use it when all you have is a raw name and no id (typeahead: company) - current_title (=, like, in) — current job title (typeahead: title) - current_job_location (=, like, in) — current job location, city/state (typeahead: location) - current_company_industry (=, like, in) — industry of current employer, Capitalized (e.g. "Information Technology & Services", "Computer Software", "Hospital & Health Care", "Financial Services", "Marketing & Advertising") (typeahead: company_industry) - current_company_category (=, like, in) — category of current employer, lowercase (e.g. "software", "consulting", "financial services", "e-commerce", "health care") (typeahead: category) - current_company_size (=, in) — size range: "2-10", "11-50", "51-200", "201-500", "501-1000", "1001-5000", "5001-10000", "10001+" - current_company_id (=, in) — exact company match by id. PREFERRED whenever you target a specific company: pass the company id (e.g. "org_xxx") from a search_company / enrich_company result. Unlike current_company (name), this never pulls in other companies that share the name - current_employment_type (=, in) — "Full-time", "Part-time", "Self-employed", "Freelance", "Contract", "Permanent", "Permanent Full-time", "Permanent Part-time", "Contract Full-time", "Contract Part-time", "Internship", "Apprenticeship", "Seasonal" - years_in_current_position (=, >, >=, <, <=, between) — years in current role - years_at_current_company (=, >, >=, <, <=, between) — years at current company - current_company_has_funding (=) — bool, whether the current company has received funding - current_company_funding_stage (=, in) — funding stage of current company. Values: seed_round, series_a, series_b, series_c, series_d, series_e, series_f, series_g, series_h, series_unknown, pre_seed_round, angel_round, grant, private_equity_round, debt_financing, convertible_note, corporate_round, equity_crowdfunding, post_ipo_equity, post_ipo_debt, post_ipo_secondary, secondary_market, non_equity_assistance, product_crowdfunding, initial_coin_offering, undisclosed. Legacy values without _round suffix also exist (seed, p…typeahead
ChatGPTHelper to autocomplete a valid filter value. This is NOT a search tool — call a search tool to actually retrieve people/companies. Use typeahead to resolve the exact stored value for a free-text categorical filter (company, industry, title, skill, school, investor, location, category). Don't hesitate to use it when: the query is complex, you're unsure which filter value or column fits the user's intent, a search returned few or no results, or the user explicitly asks for autocomplete suggestions — then retry the search with the resolved value. Returns canonical values with a popularity bucket. Each returned result costs a small amount of credits; empty result sets are free.
