> ## Documentation Index
> Fetch the complete documentation index at: https://infercrane.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# FinOps and advisory Autopilot

> Explain sourced inference cost and create human-approved serving recommendations.

# FinOps and advisory Autopilot

InferCrane treats cost as evidence, not a guess. A FinOps report accepts only cost metadata carrying a
source and observation time. Missing cost remains unavailable, currencies are never silently converted,
and avoidable spend remains unknown until utilization and a qualified alternative directly support it.

```bash theme={"theme":{"light":"github-light-default","dark":"vesper"}}
infercrane finops coder-production --window 720h
```

The report persists its exact evidence, evaluation window, disclosure set, and canonical input digest.

## Advisory Autopilot

Autopilot consumes the deterministic SLO recommendation already persisted for a deployment:

```bash theme={"theme":{"light":"github-light-default","dark":"vesper"}}
infercrane recommend coder-production
infercrane autopilot plan coder-production --objective minimize_cost
infercrane autopilot approve PLAN_ID
```

`plan` creates an immutable evidence snapshot. `approve` records the authenticated human decision. Neither
command changes a deployment, provisions capacity, or promotes a revision. The next production step is an
ordinary explicit candidate rollout followed by Replay, benchmark, and Release Guard.

<Warning>
  Approval is not execution. InferCrane intentionally has no autonomous production mutation path.
</Warning>