# Model migration decision

Blank working document. Replace placeholders with your own evidence; an empty field is unknown, not a passing result.

Owner: [fill in]
Source revision: [fill in]
Environment: [fill in]
Evidence date: [fill in]

## Workload contract

Current endpoint: ___
Required modalities/context/output/tools: ___
Requirement evidence: ___
Data residency/privacy conditions: ___

## Candidate

Exact endpoint and source/date: ___
Supported requirements: ___
Unknown or missing requirements: ___
Preflight input/output: ___

## Evaluations

| Required case ID | Current result | Candidate result | Actual billed usage/evidence |
| --- | --- | --- | --- |
| ___ | not run | not run | unknown |

## Rollout decision

Unresolved blockers: ___
Canary scope and observation window: ___
Rollback trigger/owner: ___
Authorised API budget: ___
Decision: pending

## Boundaries

- Benchmark position does not prove tool-call, vision or application compatibility. Missing, duplicate or failed required evaluations block a preflight pass.

- API calls, private input transfer and a canary can incur cost or affect people. The local checker runs none of those actions and does not verify vendor specifications.

Workflow: https://undominated.ai/workflows/#plan-a-model-migration

Original worksheet: MIT. Linked resources retain their own licences and setup requirements.