> 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/home/edge-pipeline/edge-pipeline-overview.md).

# Edge pipeline overview

How IntelFactor produces inspection outcomes at the edge.

The edge pipeline exists to produce timely, auditable inspection outcomes without disrupting production.

### High-level flow

1. Observe the production process.
2. Evaluate what is observed against inspection intent.
3. Produce a structured inspection outcome.
4. Capture evidence artifacts for traceability.
5. Publish results for local and (optionally) cloud visibility.

### What’s guaranteed here

* Outcomes are produced locally.
* Evidence is retained as structured artifacts.
* The system favors continuity and predictable behavior.

### Key supporting docs

* [Evidence & retention policy](/docs/home/edge-pipeline/evidence-and-retention-policy.md)
* [Data model: causal triples](/docs/home/edge-pipeline/data-model-causal-triples.md)

### What’s intentionally abstracted

* Internal decision logic.
* Environment-specific tuning.
* Site-specific deployment procedures.