> ## 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.
> 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.

# News

> Find current reporting, industry coverage, and emerging stories with Exa Search.

Use Exa Search for reporting from major publications, trade press, and niche outlets. New articles become searchable within minutes of publication. Combine a natural-language query with date filters when the publication window is a hard requirement.

## Use it for

* Market and investment research
* Cybersecurity and threat intelligence
* Company, product, and competitor monitoring
* Industry briefings and current-event research

## Example queries

### Follow a developing policy story

Name the topic, source type, and publication window so the results focus on the current phase of the story.

```text theme={null}
news coverage of the EU AI Act enforcement timeline published this month
```

### Find practitioner analysis

Name the source type when you want analysis from practitioners rather than general news coverage.

```text theme={null}
engineering blog posts about migrating from Postgres to ClickHouse
```

### Discover discussions in a specific format

Include the format and the subject in the query. This keeps the search open to episode pages and transcripts across the web.

```text theme={null}
podcast episodes where founders discuss pricing strategy mistakes
```

### Research adverse media

Describe both the negative signal and the entity class you are investigating. Avoid reducing the query to a company name plus the word “news.”

```text theme={null}
negative press and regulatory complaints about payday lending companies
```

## Make a request

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

  exa = Exa()

  results = exa.search(
      "news articles about AI regulation updates in the European Union",
      type="auto",
      num_results=10,
  )
  ```

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

  const exa = new Exa();

  const results = await exa.search(
    "news articles about AI regulation updates in the European Union",
    {
      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": "news articles about AI regulation updates in the European Union",
      "type": "auto",
      "numResults": 10
    }'
  ```
</CodeGroup>

## Get structured data with Exa Agent

For structured data that requires research across multiple sources, use an [Exa Agent task run](/docs/agent/quickstart). Describe the stories, fields, and time window you need, and Agent returns schema-validated results with citations.

<Card title="Start an Agent task" icon="bot" href="/docs/agent/quickstart" cta="Open Agent guide" arrow="true">
  Build a sourced news brief, compare coverage, or extract normalized facts from a developing story.
</Card>