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

# Deep Research

> Typed, cited research briefs that ground recommendation ranking and the implementation context for automated discovery PRs, plus the Remyx bot

**Nav:** Discover > Deep Research

Topical matching tells you what a paper is about. It doesn't tell you where an approach sits in the field, what's still unsolved, or which concrete change is worth trying in your repo. When you point Remyx at a repo, it runs a research pass that answers those questions and stores the result as a **research brief** that both ranking and drafting read from.

***

## Research briefs

A **research brief** is a typed, cited summary that Remyx produces and stores **section-grained** for a repo, so each section is addressable on its own. A brief contains:

| Section               | What it holds                                          |
| --------------------- | ------------------------------------------------------ |
| **Domain framing**    | What problem space the repo sits in and why it matters |
| **Approaches survey** | The methods in use across the field, with tradeoffs    |
| **Future directions** | Where the work could plausibly go next                 |
| **Candidate changes** | Concrete, implementable changes worth trying           |
| **Citations**         | The sources behind every claim above                   |

Because the brief is typed and cited, ranking and drafting can pull just the section they need, and you can trace any claim back to its source.

***

## How briefs are created and used

A brief is created automatically when you create a [Research Interest from a GitHub repo](/platform/discover/feed#research-interests-from-a-repo). Remyx runs the deep-research pass in the background; you don't trigger it separately.

Once stored, the brief is used in two places:

<CardGroup cols={2}>
  <Card title="Recommendation ranking" icon="ranking-star" href="/platform/discover/feed#how-recommendations-are-ranked">
    The brief's **future directions** become a forward-looking ranking axis alongside your shipping history, so the feed can weigh where the work is headed. The **candidate changes** seed recommendations directly.
  </Card>

  <Card title="Automated-PR drafting" icon="compass" href="/platform/discover/outrider">
    When Remyx's [automated discovery PRs](/platform/discover/outrider) (a feature called **Outrider**) draft an implementation against your repo, the stored brief is part of the context they work from, alongside the recommendation and your repo's history.
  </Card>
</CardGroup>

***

## The Remyx bot

You can ask about a brief and a run from the pull request or issue itself: any PR or Issue that Remyx's [automated discovery PRs](/platform/discover/outrider) (**Outrider**) opened.

<Steps>
  <Step title="Mention the bot">
    In a comment on such a pull request or issue, mention **`@remyx-ai`** (aliases `@remyxai` and `@remyx` also work) and ask your question.
  </Step>

  <Step title="It acknowledges">
    The bot posts a 👀 reaction so you know the mention was picked up.
  </Step>

  <Step title="It replies once">
    It posts a single grounded reply as `remyx-ai[bot]`, retrieved over the stored research brief plus that run's telemetry: the recommendation runs, their outcomes, and rejected candidates.
  </Step>
</Steps>

Because it answers from the brief and the run's own telemetry, you can ask things like:

* "Why was this recommendation surfaced over the others?"
* "What did the brief say about alternatives to this approach?"
* "Which candidate changes were considered and rejected for this run?"

<Warning>
  **The Remyx bot is read-only this phase.** It answers questions; it does not take write actions, edit code, push commits, or change PR state. A human stays at every decision.
</Warning>

It only responds when **all** of these hold:

* The comment **mentions the bot** (`@remyx-ai` / `@remyxai` / `@remyx`).
* The comment is on a pull request or issue that [automated discovery PRs](/platform/discover/outrider) opened.
* The **permission check** passes.

If any condition fails, no reply is posted.

***

## Paper enrichment and PDF code-link recovery

A recommendation is only actionable if you can find the code behind it. Two background steps make more papers implementable. Both need nothing from you and run at ingest.

<AccordionGroup>
  <Accordion title="Paper enrichment" icon="link">
    For a paper with no code link, an enrichment agent traverses the arXiv abstract and HuggingFace papers pages through to project pages, classifies the URLs it finds, resolves licenses, and recovers GitHub, HuggingFace, and SPDX links back into the paper record. Existing fields are left alone; it only fills empties.
  </Accordion>

  <Accordion title="PDF code-link extraction" icon="file-pdf">
    Remyx fetches the paper's PDF and promotes a `Code:`, `Project page:`, or `Repository:` URL directly into the paper record at ingest. Downstream, that named reference repo is lifted into the implementation launch context for [automated discovery PRs](/platform/discover/outrider) as the **source of truth**, so the agent translates from the reference and diffs against it before opening a PR.
  </Accordion>
</AccordionGroup>

More papers then arrive with a named reference repo already attached. That is the difference between a recommendation you can act on now and one you'd have to go find the code for first.

***

## Related

<CardGroup cols={3}>
  <Card title="Feed" icon="newspaper" href="/platform/discover/feed">
    Repo-backed interests trigger a brief that feeds ranking
  </Card>

  <Card title="Automated discovery PRs" icon="compass" href="/platform/discover/outrider">
    The scheduled agent (Outrider) that drafts PRs from the brief
  </Card>

  <Card title="Continuous Experimentation" icon="arrows-rotate" href="/concepts/continuous-experimentation">
    How discovery, briefs, and implementation form a loop
  </Card>
</CardGroup>