Primitives

Search Companies by Tech Stack with Intent

Asynchronous, LLM-verified variant of Search Companies By Tech Stack. Same tech-in-job-postings search, plus an activity you supply - each company’s most recent matching posting is verified against that activity, and only companies whose posting demonstrates the tech being used in the way you described are returned.

No API key yet? Sign up via Agent Auth to get your X-API-Key - the only required header for this endpoint.

Use it when the tech mention alone is too noisy and you care how the tech shows up:

tech=Snowflake + activity=migrating off Redshift to Snowflake
tech=Kubernetes + activity=migrating workloads from VMs to Kubernetes
tech=dbt + activity=building a central analytics engineering team that owns dbt models

The activity acts as a hard filter: if the posting mentions the tech but in a different context (a customer reference, a different product with the same name, an unrelated use-case), the company is dropped. Each returned company carries an intent.reason quoting the exact posting phrases that support the verdict, plus the qualified posting itself (intent.qualified_job).

How it runs

The call returns a job_id immediately and the scan runs as a background job: companies are verified in ranked order (most matching posts first) and the scan early-stops once limit companies qualify - you only pay for what you asked for. A broad activity completes in under a minute; a rare one scans deeper and can take a few minutes.

Poll GET /api/v2/tech/companies/intent-search/{job_id} (“Tech Intent Search Results”, listed under Agent Helpers) until status is completed, then walk the result pages using next_cursor.

Filters & enrichment

All the firmographic filters from Search Companies By Tech Stack work here (hq_country_code, min_employee_count, max_employee_count) and auto-enable enrichment. Set enrich=true without filters to hydrate qualified companies with firmographics (employee count, HQ, website, LinkedIn, industries, funding, revenue).

Credits

Charged 20 credits per qualified company returned, when the job completes - empty result sets are free. The exact amount is echoed in the manifest’s credits_consumed. Polling is free.

The response returns a job_id; then poll GET /api/v2/tech/companies/intent-search/{job_id} for status and results.

POST

api

tech

companies

intent-search

curl -sS -X POST "https://api.openfunnel.dev/api/v2/tech/companies/intent-search" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"tech": "Snowflake", "activity": "migrating off Redshift to Snowflake", "lookback_days": 180, "limit": 50}'

{
  "job_id": "<string>",
  "message": "<string>",
  "requested_limit": 123,
  "status": "pending"
}

Headers

X-API-Key

string

required

Body

application/json

Request body for the async tech + activity-intent search. Same search inputs as Search Companies By Tech Stack, plus the required activity to verify and a limit on qualified companies.

tech

string

required

Technology to search for in job descriptions (e.g. 'Snowflake', 'Kubernetes').

Required string length: 1 - 128

activity

string

required

The activity intent to verify, e.g. 'migrating off Redshift to Snowflake' or 'building a central analytics engineering team that owns dbt models'. Acts as a HARD filter: a company qualifies only when its job posting mentions the tech in a way consistent with this activity.

Required string length: 1 - 500

Examples:

"migrating off Redshift to Snowflake"

"migrating workloads from VMs to Kubernetes"

variations

string[] | null

Optional alternate phrasings of the tech (e.g. 'K8s' for Kubernetes). Each is OR-matched as a phrase.

lookback_days

integer

default:365

Lookback window in days (1–365).

Required range: 1 <= x <= 365

limit

integer

default:100

Maximum number of QUALIFIED companies to return. The scan walks the ranked pool and early-stops once this many companies pass intent verification.

Required range: 1 <= x <= 500

exclude_vendor

boolean

default:true

When true (default), excludes job posts from the vendor of the technology being searched.

exclude_aggregators

boolean

default:true

Exclude well-known LinkedIn job aggregators and reposters (jobs-via-*, lensa, ziprecruiter, etc.). ON by default.

exclude_company_slugs

string[] | null

Additional LinkedIn company slugs to exclude on top of the default aggregator block-list.

enrich

boolean

default:false

Hydrate qualified companies with firmographics (employee count, website, LinkedIn, HQ, industries, funding, revenue). Auto-enabled when any firmographic filter is set.

hq_country_code

string | null

Filter by company HQ ISO 3166-1 alpha-3 code (e.g. USA, GBR, IND, DEU). Full list of 250 codes via GET /api/v2/tech/country-options (under Agent Helpers). Auto-enables enrich.

Required string length: 3

min_employee_count

integer | null

Inclusive lower bound on company employee count. Auto-enables enrich.

Required range: x >= 0

max_employee_count

integer | null

Inclusive upper bound on company employee count. Auto-enables enrich.

Required range: x >= 0

Response

Job accepted. Returns a job_id to poll for status and results.

Returned immediately when a tech intent-search job is submitted.

job_id

string

required

Async job id. Poll GET /api/v2/tech/companies/intent-search/{job_id} for status and results.

message

string

required

Human-readable next-step hint.

requested_limit

integer

required

The requested maximum number of qualified companies.

status

string

default:pending

Job status at submit time (always pending).

Deep ResearchDecide whether a single, known company fits your criteria in terms of recent activity and organizational structure as a qualifier. <Info>**No API key yet?** [Sign up via Agent Auth](/agent-auth/agent-auth/agent-sign-up) to get your `X-API-Key` - the only required header for this endpoint.</Info> Combine an activity question (answered from job postings) and a team-composition question (answered from LinkedIn people) in a single call, with cited evidence per stage. Provide a `domain` plus at least one of `activity_question` or `qualifier_question`. Each parameter is hard-wired to a specific data source - pick the one that matches where the answer lives: - **`activity_question`** → answered from the company's **recent job postings**. Use for hiring intent, team expansion, tech-stack adoption visible in JDs, geographic hiring footprint (e.g. "hiring SDRs", "building an AI platform team", "hiring engineers experienced with Rust and Kubernetes", "posting data roles that require Snowflake and dbt", "expanding in Berlin"). - **`qualifier_question`** → answered from **LinkedIn people data** (current-employee profiles). Use for team composition, roles already filled, org structure (e.g. "has a Head of Security", "has ≥5 SDRs and a Sales Director", "has a dedicated AppSec team"). Pass both when a question spans both signals - each stage runs against its own data source and returns independent evidence. Each stage returns a natural-language `answer` suitable for inline display, a boolean `qualified` verdict, and structured source evidence - `sources` with job postings for activity (title, URL, location, why-relevant reason) and LinkedIn profiles for qualifier (name, title, LinkedIn URL, seniority, department). Credits: charged **per call**, not per source returned. 1 successful call (at least one stage produced a finding) = 1 charge at the per-call price configured for your workspace. A 404 (domain could not be resolved) is free. The exact amount billed is returned in `credits_consumed` on every response.

⌘I

curl -sS -X POST "https://api.openfunnel.dev/api/v2/tech/companies/intent-search" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"tech": "Snowflake", "activity": "migrating off Redshift to Snowflake", "lookback_days": 180, "limit": 50}'

{
  "job_id": "<string>",
  "message": "<string>",
  "requested_limit": 123,
  "status": "pending"
}