Create a concise run-record template for this AI task.
Fields: task purpose, permitted source/version, instruction/version,
observed tool label, actual output files, revisions, performed checks,
remaining questions and publication or approval state.
Keep unknown fields explicitly unknown. Separate prepared examples from
recorded outputs. Do not infer time savings, quality scores, model names
or approvals that the evidence does not supply.

---

Turn these performed checks into a short evidence record.
For each, name the artifact/version, exact check, observed result and
remaining limitation. Do not turn a local file check into a live
deployment claim or a prepared example into an actual AI response.
Preserve failed checks and connect each repair to the new output version.

---

Read this run record as the colleague receiving the work.
Identify the source, current output, material correction, performed
checks and next decision. Ask a focused question for any missing item.
Replace an unsupported 'approved' or 'deployed' label with the actual
observed state. Keep the record short enough to use.
