Produce a Visual Artifact
Answer one reader question in the least complex adequate medium. A visual is output. Comprehension remains unproved.
Use when. A reader question, permitted claims, and an owner are supplied.
Do not use when. The question, permitted claims, or owner is missing, or you want the model to publish.
Your input. Reader question; permitted claims and facts; medium constraints; named owner.
Your quality check. The visual answers the question without inventing facts. Publication stays blank.
Put this to work
Prepare one visual artifact
For the named visual ownerCopy this prompt. Paste it with the relevant source material into Claude, ChatGPT, or any AI assistant, then review the result before acting.
Human decision — cannot be delegated. Accept the visual, revise it, or stop. AI may draft only. No clinic CTA.
Outcome
One visual plus a note of the medium, the claim it may show, and the human decision.
Use When
Use when a reader question, permitted claims, and an owner are supplied.
Inputs
Reader question; permitted claims and facts; medium constraints; named owner.
Recipe
Copy the prompt. Paste only supplied material. Leave the human decision blank.
Human and AI Control
An assistant may draft and report. Named owner accepts the visual and controls publication and spend. The tool is a player, not the job.
Output and Handoff
Return the Visual artifact and the blank human decision.
Evidence and Stop
Demand is hypothesized and the outcome is untested. Stop when the owner, the job boundary, or a required input is missing.
Reliability
Skill and tool: visual production using a replaceable image or diagram tool. The Visual artifact is the pattern; least adequate medium and human acceptance is the protocol. Retain the returned brief as evidence. Accept only a result the named human can verify against the supplied inputs.
Next
Return the result to the named owner. Do not register autonomous execution until a completed prompt trial and an accepted execution contract exist.