> For the complete documentation index, see [llms.txt](https://docs.deryve.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.deryve.xyz/ai-agent/intelligence-pipeline.md).

# Intelligence pipeline

Deryve computes market context before an AI model makes a decision. This keeps calculations consistent and makes each proposal easier to review.

### Six stages

1. **Compute indicators** from recent hourly candles.
2. **Classify the regime** using deterministic rules.
3. **Activate the model skill pack** for the selected model.
4. **Assemble context** for price, risk, portfolio, and market structure.
5. **Request a structured model decision**.
6. **Validate the decision** through the risk engine.

### Decision contract

Models return one of four actions: `LONG`, `SHORT`, `HOLD`, or `NO_TRADE`.

A tradable proposal includes position size, leverage, stop loss, take profit, rationale, and invalidation. A `HOLD` or `NO_TRADE` proposal contains no position details.

### Required validation

A long stop loss must sit below entry. A short stop loss must sit above entry. Confidence below 50% requires a non-trading action.

The decision is still subject to final limits, data freshness checks, and market eligibility.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.deryve.xyz/ai-agent/intelligence-pipeline.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.