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

# Deep Research

> Multi-step research — search, read, synthesize, cite. For when one query isn't enough.

Deep Research is the heavyweight Source. It runs **multiple searches**, reads pages deeply, and writes a synthesized answer with citations. Use it for questions that a single search wouldn't crack.

Toggle it from `@`, send your prompt, and walk away — runs can take a minute or more.

<Note>
  **Screenshot coming.** Deep Research run with intermediate steps + final synthesis.
</Note>

## How it works

Behind the scenes, Foundry runs a fan-out → extract → cite pipeline:

| Step           | What happens                                                                                                             |
| -------------- | ------------------------------------------------------------------------------------------------------------------------ |
| **Search**     | The primary search engine (Exa) returns \~8 high-signal results. If Exa returns nothing, Foundry falls back to Parallel. |
| **Extract**    | Foundry pulls long-form content from the top pages via Firecrawl.                                                        |
| **Read**       | The model reads the extracted content into context.                                                                      |
| **Synthesize** | The model writes a structured answer with citations to every claim.                                                      |

You'll see status updates while it runs — "Searching", "Extracting", "Reading", "Writing". Tab away if you want; [browser notifications](/foundry/chat/notifications) will ping you when the answer lands.

## When to use it

* **Market or competitive landscapes** — *"compare the top 5 prompt-optimization platforms"*.
* **Long-form factual digs** — *"what's the current state of evidence on cold plunges"*.
* **Hard research questions** — anything you'd otherwise spend half a day on with tabs.

## Good for

* *"Summarize every Anthropic paper from 2024 with one-line takeaways."*
* *"Find every YC company in the AI infrastructure space funded in the last 6 months."*

## Limits

* It's slower. Expect a minute or more for non-trivial prompts.
* It's more expensive — multiple searches + extractions cost more than a single Web call.
* The answer is only as good as the sources. Niche topics with thin web coverage produce thinner answers.

## Tips

* **Be specific.** "Compare X, Y, and Z on dimensions A, B, C" outperforms "tell me about X, Y, Z".
* **Pair with browser notifications** so a long run doesn't tie you down.
* **Open citations** to verify any claim that surprises you.

## Related

<CardGroup cols={2}>
  <Card title="Web" icon="globe" href="/foundry/sources/web">
    Single-shot search.
  </Card>

  <Card title="Connectors: Firecrawl" icon="plug" href="/foundry/connectors/pre-installed">
    The page extractor under the hood.
  </Card>
</CardGroup>