# Causal triples

Causal triples capture a defect, a hypothesis, and an action.

```mermaid
flowchart LR
  D[Defect observed] --> C[Cause hypothesis]
  C --> A[Suggested action]
  A --> O[Outcome measured]
  O --> T[(Stored as triple)]
  T --> F[Feedback loop]
  F --> C
```

### How to read this

* Triples are versioned and auditable.
* Feedback strengthens or weakens hypotheses over time.
* The operator can confirm, reject, or annotate.

### Next steps

* [Decision model](/doc/intelfactor-ai/product-concepts/decision-model.md)
* [Local RCA engine](/doc/intelfactor-ai/product-concepts/local-rca-engine.md)
* [Evidence packaging](/doc/intelfactor-ai/architecture-and-data/evidence-packaging.md)


---

# Agent Instructions: 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:

```
GET https://intelfactor.gitbook.io/doc/intelfactor-ai/product-concepts/causal-triples.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.