A quick overview for up to 10 people in one call

Required permissions: research:trigger.

Returns every overview in the same response. One person typically takes 2–3 seconds, and people are synthesized several at a time, so a full 10-person call takes a small multiple of that rather than 10 times it. The server stops after 120 seconds by default with 503 research_failed. Set your client timeout above 120 seconds and retry once on retry_later. Each call generates a new answer. It saves nothing to your workspace. The company or person does not need to be in your workspace. This is the same quick overview the Trayo app shows. Public REST and MCP usage is recorded without daily usage caps, workspace quota cutoffs or lookup quotas for now. Workspace request pacing still applies.

Same as POST /v1/research/person, once per person in people (1 to 10), reading the workspace seller context once for the whole batch. Always ungrounded — grounded is not accepted here. A person that cannot be resolved, or whose overview comes back empty (person_profile_too_thin), lands in errors by index with a code and a retry class, and never fails the rest of the batch. Only the overviews in results draw on the quota — a person in errors does not.