The outcome

Return inspectable search evidence for an AI workflow instead of an unsupported synthesized answer.

Exa is a web search, content retrieval, and research API for AI applications. Finding web sources with semantic and filtered search, retrieving page contents, and supplying inspectable evidence to research or agent workflows. This guide narrows that broad capability into one repeatable outcome, with checkpoints that keep the source material and your judgment in the loop.

Before you begin

Set the boundary before the tool starts.

Choose one real task, identify who will use the result, and decide what evidence or test will make the result acceptable. Gather only the source material needed for that task. If the work contains confidential, personal, regulated, or client-owned information, confirm that the platform and account are approved before sharing it.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

Step by step

A workflow you can repeat.

  1. 01

    Define the information need, acceptable source types, freshness window, excluded domains, evidence fields, and maximum result budget.

  2. 02

    Choose a search mode for the latency and depth required, and use explicit domain, category, date, and result-count filters.

  3. 03

    Request highlights or text only when needed, enable moderation for exposed user queries, and preserve URL and publication metadata.

  4. 04

    Evaluate ranking and coverage against a benchmark with expected sources, difficult queries, duplicates, and no-good-result cases.

  5. 05

    Pass evidence and citations—not hidden concatenated context—to generation, then record request ID, cost, and retrieval settings.

Working standard

What good use looks like.

  • Keep source filters explicit.
  • Evaluate retrieval separately from synthesis.
  • Preserve URLs and publication metadata.

Search results and page contents can be wrong, stale, malicious, copyrighted, or sensitive. Protect keys, constrain domains and cost, moderate exposed queries, treat retrieved text as untrusted, preserve citations, and verify evidence before action or publication.

Official references

Check the current product documentation.

Features, plan limits, availability, and data controls change. These official pages are the starting points used for this collection.