For AI agents: a documentation index is available at the root level at /llms.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Queues one enrichment run per listed entity and person, in order, each owned by the authenticated principal and billed exactly as the single-record enrich call is. A repeated id is filed once. Returns one outcome per distinct record: its run, or a refusal (NOT_FOUND, ALLOWANCE_EXHAUSTED, AMBIGUOUS, SUBSCRIPTION_REQUIRED) for a record that cannot be filed; other records still file, and runs already filed stay queued. A caller without a research subscription gets 402 before any run is filed. A transient failure fails the request; retrying it reuses runs still in progress without charging them again. A list longer than the configured batch limit is refused before any run is filed. Check each run's progress with GET /v1/harness/runs/{runId} (CLI: harness runs get).
Authentication
AuthorizationBearer
User bearer token: an aVenture API key, an OAuth access token, or a signed-in session token
Request
This endpoint expects an object.
entityIdlist of stringsOptional
Canonical entity UUIDs to enrich, filed in order before any person
modeenumOptional
COMPREHENSIVE (the default) researches each whole profile; INDIVIDUAL runs only the tasks named in taskPresetKey
Allowed values:
modelstring or nullOptional
Model id for each run’s lead agent; omit to use aVenture’s default model
personIdlist of stringsOptional
Canonical person UUIDs to enrich, filed in order after every entity
taskPresetKeylist of strings or nullOptional
Task preset keys that scope or emphasize every run; at least one is required when mode is INDIVIDUAL, and an unknown key is a 400
userPromptstring or nullOptional
Plain-language instruction for every run, such as which facts or sources to check first
Response headers
X-RateLimit-Limitinteger
Requests allowed per client IP in the current rate-limit window.
X-RateLimit-Remaininginteger
Requests left before the tightest applicable rate-limit bucket rejects.
X-RateLimit-Resetinteger
Seconds until the exhausted rate-limit bucket admits another request; 0 when none is exhausted.
Response
One outcome per distinct requested record, in request order.
recordobject
The requested entity or person
refusalenum or nullOptional
Why no run was filed; absent when run is set
Allowed values:
runobject or nullOptional
The queued or reused run; absent when refusal is set
Errors
400
Bad Request Error
401
Unauthorized Error
402
Payment Required Error
403
Forbidden Error
406
Not Acceptable Error
409
Conflict Error
415
Unsupported Media Type Error
422
Unprocessable Entity Error
429
Too Many Requests Error
500
Internal Server Error
503
Service Unavailable Error
Queues one enrichment run per listed entity and person, in order, each owned by the authenticated principal and billed exactly as the single-record enrich call is. A repeated id is filed once. Returns one outcome per distinct record: its run, or a refusal (NOT_FOUND, ALLOWANCE_EXHAUSTED, AMBIGUOUS, SUBSCRIPTION_REQUIRED) for a record that cannot be filed; other records still file, and runs already filed stay queued. A caller without a research subscription gets 402 before any run is filed. A transient failure fails the request; retrying it reuses runs still in progress without charging them again. A list longer than the configured batch limit is refused before any run is filed. Check each run’s progress with GET /v1/harness/runs/{runId} (CLI: harness runs get).
