The social-campaign sequence that finally worked — hook, data point, contrarian take, thread — preserved as a workflow prompt that runs the whole recipe in order.
Some conversations converge on a SEQUENCE, not a single output: the four-beat social campaign, in that order, with standalone-post and length rules. Workflow mode preserves the sequence as the conversation shaped it — the order is part of what the iteration earned, and the prompt carries it with the per-step rules intact. The boundary is deliberate: this carries the workflow the conversation already designed; designing multi-step workflows from scratch is the Multi-Step Prompt Builder, and the usage notes say so. This setup loads the campaign chat whose sequence is the asset.
Recognize the sequence
Day one hook, day three data, day five contrarian, day seven thread — order IS the convergence.
Preserve it whole
Workflow mode keeps the beats in order with their standalone and length rules.
Run per input
Each new blog post runs the same four-beat recipe — iteration designed it once.
Workflow mode preserves the sequence the conversation converged on — here the four-beat campaign (day one hook, day three data point, day five contrarian take, day seven link thread) travels in that exact order with its per-step rules, like "under 280 characters except the day-seven thread." The Conversation-to-Prompt Builder distills it into one prompt you run per new blog post in your assistant.
Rejected directions travel as an AVOID list ("ten link-drops is noise, not a campaign"), so the model can't rediscover a path you already walked back. The prompt also states that later requirements override earlier ones where they conflict, matching how the conversation actually resolved. If the sequence outgrows one prompt, the usage notes point you to the Multi-Step Prompt Builder to design it properly.
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.