Prompt Engineering

Create a Template From a Conversation — One Slot, Fixed Recipe

A case-study chat that converged on the three-beat structure becomes a template: {{input}} changes per customer, everything the iteration earned stays fixed.

Overview

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.

Workflow

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.

Why This Works

Recipe-plus-slot matches how converged structures actually get reused
One explicit slot keeps the template honest about what varies
The PVB handoff composes the tools instead of duplicating them

Best for

Repeating tasks with one changing subject
Content series with fixed converged structure
Teams running many instances of one recipe

Not for

Building templates from scratch with full variable management — the Prompt Template Builder
Detecting ALL changeable values in an existing prompt — the Prompt Variable Builder (the package points there)

Use cases

Case studies, profiles, and other per-subject recipes
Templating a structure that converged once
Feeding distilled prompts into the variableization pipeline

Customize This Resource

Opens this scenario in Conversation-to-Prompt Builder. Distill to get the reusable prompt — then adjust the output mode.

Open in Conversation-to-Prompt Builder

Prompt Template

REUSABLE PROMPT
--------------------------------
TASK (template)
Write a customer case study from an interview transcript. — for {{input}}.

REQUIREMENTS (earned through iteration — later items override earlier ones where they conflict)
- Instead, structure it as: the breaking point, the change, the number that proves it.
- This is better. Keep the three-beat structure.
- Exactly right. I'll reuse this for every case study interview.

CONSTRAINTS
- [No hard constraints detected — add any that must hold]

FORMAT
- Format: 600 words max, one pull quote, no bullet lists.

AVOID (rejected during the conversation — do not reproduce these)
- Too generic — "great results" is exactly what case studies drown in.

QUALITY BAR
Match the version the conversation accepted — the reaction was: "Exactly right. I'll reuse this for every case study interview."
If anything above is ambiguous or conflicting, say so and ask — do not silently pick one reading.
--------------------------------

WHY THIS PROMPT WORKS
- It starts where the conversation ENDED: the corrections and accepted preferences are requirements now, not future feedback.
- The last decision wins: the prompt states that later requirements override earlier ones, the way the conversation actually resolved.
- Rejected directions travel as an AVOID list — the model cannot rediscover the paths you already walked back.

PRESERVED REQUIREMENTS
- Corrections carried: 1 · Accepted preferences: 2 · Standing rules: 0
- Constraints: 0 · Format decisions: 1

REJECTED DIRECTIONS
- Too generic — "great results" is exactly what case studies drown in.

OPTIONAL VARIABLES
- {{input}} — the subject that changes per use (already placed in the task line).
- To detect more changeable values, run the prompt through the Prompt Variable Builder.

USAGE NOTES
- Replace {{input}} with each use's subject before sending — everything else stays fixed.
- For deeper variableization (detecting more changeable values), run this prompt through the Prompt Variable Builder.
- Distillation confidence: High.
- Signals were extracted VERBATIM from the conversation (deduplicated, never paraphrased) — read the prompt once before trusting it with a real run.

Related Resources

Explore more resources that work well with this one.

More from Conversation-to-Prompt Builder

Convert a Conversation to a Prompt — the Full Anatomy Turn a Chat Into a Prompt — Start at the Result Convert a Feedback Thread to a Prompt — Rejections Are the Asset

View all Conversation-to-Prompt Builder resources →

Adjacent Workflows

AI Session Handoff — Shift Change for Working Sessions Context Handoff Builder API Request Variable Builder Prompt Variable Builder Agent Task Template Prompt Template Builder

Related Tools

Conversation-to-Prompt Builder

Used in Playbooks

Complete workflows that include this resource as a step.

AI Reusable Prompt Template Workflow Workflow · 3 steps

Tip: Save time by exploring related resources and tools that integrate with this workflow.

Explore all resources