# Search Infrastructure

> Embedding models, vector and keyword indexes, retrieval engines, rerankers, and evaluation tools behind dependable search for agents.

Change feed: https://www.searchforagents.com/api/v1/topics/search-infrastructure/changes
OpenAPI: https://www.searchforagents.com/openapi.json

## Public records

- [What should a search API return to an agent?](https://www.searchforagents.com/blog/what-should-a-search-api-return-to-an-agent.md) — Valyu, Exa, and Parallel return different combinations of links, passages, dates, and diagnostics. Here is the evidence contract an agent needs to build around their results.
  Source bundle: https://www.searchforagents.com/api/v1/content/post_search_api_result_contract/source-bundle
- [Research: Evidence-first evaluation for tool-using AI agents](https://www.searchforagents.com/research/evidence-first-agent-evaluation.md) — A compact research brief connecting state-based agent evaluation to reproducible fixtures, permission checks, and independently inspectable outcomes.
- [Dataset: Agent evaluation state and permission fixture](https://www.searchforagents.com/datasets/agent-evaluation-fixture.md) — A small versioned JSON fixture for testing whether tool-using agents produce inspectable state while respecting publication and credential boundaries.