> 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/reliability-and-operations/observability-local.md).

# Observability (local)

What to monitor on-site without relying on cloud.

IntelFactor supports fully local observability.

### Metrics to monitor

* Inference latency (p50/p95/p99).
* FPS and frame drops vs line speed.
* GPU utilization.
* Queue depth and buffer growth.
* Disk utilization (evidence partition).
* Camera health heartbeat.
* Defect rate drift vs baseline.
* RCA response time (when triggered).

### Expected outcome

Operators and QA can see station health, shift summaries, and RCA recommendations without cloud connectivity.