Company Signals

Ask structured research questions about companies and receive cited AI answers that can power scoring, qualification, and CRM fields.

Overview

Company signals answer structured research questions about a company. Use the synchronous endpoint for most interactive workflows, and use async or batch endpoints when you need webhook delivery, polling, or high-volume processing.

A signal should ask one precise question and request the answer in the shape your workflow needs. Smaller, structured questions produce outputs that are easier to score, compare, and sync into CRM fields.

Choosing an execution mode

Use sync signals when:

  • A user or agent is waiting for the answer.
  • You want a single request and response.
  • The workflow benefits from simple retry behavior.

Use async signals when:

  • You need webhook delivery.
  • The answer can be collected later.
  • You want to decouple request submission from result processing.

Use batch signals when:

  • You need to run the same questions across many domains.
  • You are producing a list-level analysis.
  • You can process results asynchronously or in bulk.

Signal design

Strong signal questions are specific, observable, and tied to an action. Instead of asking whether a company is a good fit, ask about concrete evidence:

  • Whether the company is hiring for a relevant function.
  • Which products or business lines are mentioned on the site.
  • Whether the company uses or mentions a target technology.
  • Which recent events suggest expansion, churn risk, or buying intent.

Pick an answerType that matches downstream usage. Use boolean for routing, list for evidence collection, number or percentage for scoring inputs, and open_text for human-readable context.

Operational notes

  • Prefer the sync endpoint for agent and CLI workflows unless you specifically need webhooks.
  • Use timeout headers when the caller has strict latency requirements.
  • Store signal IDs when using async or batch mode so results can be retrieved later.
  • Design batch jobs around reusable templates when running large repeated research tasks.

Relevant API reference

On this page