- 01
Define the tool evaluation job
Treat “photoprompt” as a search job to investigate, not as proof that a SEELE feature exists. First clarify the requested job, observe current controls on a bounded test, and document workflow fit and evidence gaps. Write the intended audience, source owner, desired change, protected details, reviewer, and delivery condition before selecting any interface or model. That brief keeps the evaluation specific and makes an unsupported assumption visible early. During review, preserve the continuity note, and ask the factual editor to record reversal cost before the source comparison.
- 02
Prepare inputs for visual creation tools
For this topic, assemble a clear creative job, authorized references, required controls, reviewer expectations, budget context, and delivery format. Record where each source came from, who may use it, and what must remain unchanged. Use a small representative asset for the first pass, keep the original untouched, and define a fallback route so experimentation cannot silently become the production master. During review, preserve the input snapshot, and ask the factual editor to record input provenance before the source comparison.
- Confirm ownership, consent, and allowed reuse At handoff, preserve the failure note, and ask the channel editor to record identity consent before the production checkpoint.
- Preserve an untouched source and version history At handoff, preserve the authorization record, and ask the rights reviewer to record input provenance before the production checkpoint.
- Name the reviewer and acceptance condition At handoff, preserve the rights memo, and ask the identity reviewer to record reversal cost before the editorial approval.
- 03
Test observable controls for photoprompt
A bounded evaluation should inspect input support, controllability, source fidelity, revision behavior, governance, collaboration, and handoff readiness. Change one meaningful variable at a time and record the date, workspace, account context, input, setting, result, and failure. Topic selection can prioritize the question, but it does not establish availability, quality, speed, licensing, or a supported SEELE workflow. At handoff, preserve the claim inventory, and ask the model evaluator to record revision intent before the production checkpoint.
- 04
Review evidence, safety, and policy boundaries
Third-party names, pricing, features, access, and specifications require current dated first-party verification. Use only authorized media, separate observed behavior from marketing language, and check current first-party documentation for any product-specific claim. For third-party products, competitors, plans, models, and platform rules, attach a verification date and primary source; an absent statement is an evidence gap rather than proof of a limitation. At the next gate, preserve the decision history, and ask the workflow owner to record revision intent before the final sign-off.
- 05
Approve a reversible production handoff
Before advancing “photoprompt”, use a matched test asset, record the date and account context, separate observations from claims, and document tradeoffs. Document remaining manual work, unresolved evidence, destination requirements, and the person accepting the result. The handoff should preserve sources and test notes, allow correction, and avoid promises about output quality, turnaround, business performance, publishing, or access that the evidence does not support. During review, preserve the decision history, and ask the source custodian to record identity consent before the workflow transfer.