A case-study chat that converged on the three-beat structure becomes a template: {{input}} changes per customer, everything the iteration earned stays fixed.
Some convergences are recipes: the structure, rules, and quality bar stay constant while one thing changes per use. Template mode captures that shape — the converged case-study structure (breaking point, change, proving number; metric headline; 600 words; one pull quote) becomes the fixed recipe, and {{input}} marks the slot where each new customer interview goes. The usage notes route deeper variableization to the Prompt Variable Builder — distill here, variableize there, the composition the two tools were built for.
Distill the recipe
Structure, rules, and bar from the iteration — the fixed part of the template.
Place the slot
{{input}} marks what changes per use; the task line carries it.
Variableize deeper if needed
More slots? The package routes you to the Prompt Variable Builder — by design.
Everything the conversation earned stays fixed — the three-beat structure, the FORMAT line (600 words max, one pull quote, no bullet lists), and the QUALITY BAR — while a single {{input}} slot in the task line marks the one thing that changes per use. The conversation-to-prompt-builder distills that shape; you replace {{input}} each run before sending it to your own assistant.
This mode places exactly one {{input}} slot, and both OPTIONAL VARIABLES and USAGE NOTES route deeper detection to the Prompt Variable Builder — distill here, variableize there. So for a second or third slot you'd run the distilled prompt through that builder rather than expecting this one to find every changeable value.
Because directions you rejected mid-conversation travel as an AVOID list — here "Too generic — 'great results' is exactly what case studies drown in" — so the model can't rediscover a path you already walked back. Signals are extracted VERBATIM and deduplicated, and USAGE NOTES still advise reading the prompt once before trusting it with a real run.
What a converged conversation contains: a rejected voice, an accepted framing, a hard constraint, a format decision, and a final-version moment — each mapped to its prompt section.
The result you finally liked lives inside the chat. Distill the iterations into one prompt: corrections become requirements, the accepted version becomes the quality bar.
In feedback threads the rejections carry the knowledge: the mocking empty-state enthusiasm, the passive phrasing — converted into the avoid-rules that define the style.
End a working session like a shift change, not an abandonment: state captured, decisions logged, next step named — ready for the next session to pick up.
Turns a reusable API request prompt into a clean variable set covering endpoint, method, auth, payload, response format, and error handling.
A reusable AI agent task template with variables for objective, context, available tools, constraints, success criteria, failure handling, and output format.
Distill an iterated conversation into one reusable prompt — corrections become requirements, rejections become an avoid-list.
Turn a prompt that worked once into one you can reuse — pull the winning prompt out of the chat, mark the parts that change as variables, and lock it into a clean template.