> For the complete documentation index, see [llms.txt](https://intelfactor.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://intelfactor.gitbook.io/docs/intelfactor-ai/product-concepts/causal-triples.md).

# Causal triples

How “explain why” becomes structured, auditable learning.

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