# Cost and latency are quality gates

A route that answers well but blows the budget is not production-ready. Cost per successful task and p95 latency belong next to groundedness and refusal on the same scoreboard.

## What to write down

- Budget per successful task (and what counts as success) 
- p95 latency for the user-visible path 
- What happens when the budget trips: degrade, queue, or kill switch 

Re-run after model, tool, or retrieval changes. Cheap models that hallucinate more are not a saving.

## Arviser packaging

Cost or latency sits in the six audit areas. Shared metrics and CI gates pages show how to keep those numbers next to quality, not in a separate spreadsheet nobody opens.

A [24h Technical PoC Spike](/ai-poc-sprint) writes p95 latency and unit cost into the pass marks before build. For an on-device latency budget example (~15 ms WASM, 8.2 MB), see [Open proof](/#open-proof).

**Next:** [Shared metrics](/guides/shared-metrics) · [CI gates](/guides/ci-gates-llm) · [Kill switch](/guides/kill-switch) · [24h PoC Spike](/ai-poc-sprint) · [Open proof](/#open-proof) · [Request scope](/#scope)
