> ## Documentation Index
> Fetch the complete documentation index at: https://exa.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> The Exa API is served at https://api.exa.ai. Authenticate with `Authorization: Bearer $EXA_API_KEY` (or `x-api-key: $EXA_API_KEY`); create keys at https://dashboard.exa.ai/api-keys?utm_source=docs&utm_medium=docs&utm_campaign=markdown_instructions. Every way an agent can get access to Exa is described at https://exa.ai/auth.md.
> Prefer the official SDKs, `exa-py` (`pip install exa-py`) and `exa-js` (`npm install exa-js`); both read `EXA_API_KEY` from the environment.
> Tool-using agents can call Exa without writing code through the hosted MCP server at https://mcp.exa.ai/mcp, or install the Exa agent skill with `npx skills add exa-labs/agent-skills` (skill file: https://exa.ai/docs/skill.md).
> The OpenAPI specs at https://exa.ai/docs/exa-spec.yaml and https://exa.ai/docs/team-management-spec.yaml are the source of truth for request and response schemas.

# Companies & People

> Find companies, professional profiles, and the relationships between them with Exa Search. Covers people search, company search, and recruiting.

Use Exa Search as a company search and people search API for organizations and the people connected to them. These searches work best together: describe the company traits that qualify a person, or the people and roles that reveal how a company operates.

> [card] [Company retrieval benchmark](https://exa.ai/blog/company-search-benchmarks)
>
> See how Exa evaluates company retrieval and fact extraction.

> [card] [People retrieval benchmark](https://exa.ai/blog/people-search-benchmark)
>
> See how Exa evaluates targeted lookups and profile discovery.

## Use it for

* Company, candidate, and expert discovery
* Account research and stakeholder mapping
* Market maps, investment research, and deal sourcing
* Leadership, hiring, and organization research

## Write better queries

Start with the entity you want, then add the traits and relationships that qualify it. Ask for the source type when it matters, such as company homepages, professional profiles, job postings, or personal websites.

> [tab] Companies
>
> ### Discover companies by what they do
>
> Describe the customer, product, capability, stage, and geography that define the market. This finds candidates based on what they do instead of relying on a predefined company list.
>
> ```text theme={null}
> companies selling AI voice agents to dental practices
> ```
>
> ### Find operating signals
>
> Name the signal and the company traits that matter. Search can retrieve job postings, pricing pages, product documentation, and reporting alongside company pages.
>
> ```text theme={null}
> remote staff engineer roles at Series B fintech companies
> ```
>
> ### Research funding activity
>
> Specify the round, industry, participant, and time window.
>
> ```text theme={null}
> investors who led seed rounds in robotics in the last year
> ```

> [tab] People
>
> ### Discover people by role and skills
>
> Combine the role, seniority, location, relevant skills, and source type you want.
>
> ```text theme={null}
> professional profiles of senior ML engineers in Seattle with PyTorch experience
> ```
>
> ### Qualify people by company traits
>
> Describe the person's relationship to the company and the traits that qualify the company. This works better than building a company list first.
>
> ```text theme={null}
> professional profiles of founders of YC-backed developer tools companies
> ```
>
> ### Find personal websites and public work
>
> Name the profession or research area and ask explicitly for personal websites, talks, interviews, or articles.
>
> ```text theme={null}
> personal blogs of distributed systems researchers
> ```

## Search both together

Write one query that expresses the relationship you need. Exa can return company pages, professional profiles, hiring pages, and public references in the same result set.

```text theme={null}
heads of security at Series B healthcare software companies that sell to hospitals
```

## Make a request

```python Python theme={null}
from exa_py import Exa

exa = Exa()

results = exa.search(
    "heads of security at Series B healthcare software companies that sell to hospitals",
    type="auto",
    num_results=10,
)
```

```javascript JavaScript theme={null}
import Exa from "exa-js";

const exa = new Exa();

const results = await exa.search(
  "heads of security at Series B healthcare software companies that sell to hospitals",
  {
    type: "auto",
    numResults: 10,
  }
);
```

```bash cURL theme={null}
curl -s -X POST https://api.exa.ai/search \
  -H "Authorization: Bearer $EXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "heads of security at Series B healthcare software companies that sell to hospitals",
    "type": "auto",
    "numResults": 10
  }'
```

## Get structured data with Exa Agent

For structured data that requires research across multiple sources, use an [Exa Agent task run](https://exa.ai/docs/agent/quickstart.md). Describe the companies, people, qualification criteria, and output fields you need, and Agent returns schema-validated results with citations.

> [card] [Start an Agent task](https://exa.ai/docs/agent/quickstart.md)
>
> Build and qualify company or people lists, then enrich each record with fields gathered from multiple sources.