Prompt Upgrader: Rough Draft to Role-Context-Task Prompt

Turns a rough prompt into a structured one with role, context, task, constraints and output format, plus a one-line reason for each change.

You get: A text answer

More like this

The prompt

prompt-upgrader-rough-draft-to-role-context-task-prompt.md
Act as a senior prompt engineer. Upgrade the rough prompt below so ChatGPT gives a specific, usable answer.

My draft prompt: {paste your draft prompt here}

Rules:
- Keep my original intent. Do not add goals I did not state.
- If the goal, audience, or desired output is unclear, ask me one or two short questions before rewriting.
- Put any invented detail in [square brackets] so I can fill it in or delete it.
- Make constraints testable (length, tone, what to avoid) instead of vague wishes like 'be good'.

Output exactly:
1. Upgraded prompt, as one copyable block with five labeled lines: Role, Context, Task, Constraints, Output format.
2. Change log: one line per labeled part, saying what you changed and why.
3. Gaps: one line naming any missing information that would improve the result further.

Example output

AI-written example

1. Upgraded prompt

Role: You are a professional accounts-receivable specialist who writes polite, firm payment reminders for small businesses.

Context: I run [a small freelance design studio]. A client, [client first name], has not paid invoice [#1042] for [$1,800], which was due [14 days ago]. We have a good working relationship and I want to keep it. I have [not contacted them about this yet].

Task: Write a follow-up email asking the client to pay the overdue invoice and confirm a payment date.

Constraints:
- 120 words or fewer in the email body.
- Tone: friendly but direct. No guilt-tripping, threats, or mention of late fees or legal action.
- Include the invoice number, amount, and original due date in the first two sentences.
- Include exactly one clear call to action: reply with a payment date within [3 business days].
- Do not use phrases like "per my last email" or "kindly be advised".

Output format: A subject line (under 60 characters), then the email body, then a sign-off using [my name]. No explanations before or after.

2. Change log

  • Role: Added a specific specialist role so the tone and word choice match professional payment reminders instead of generic email writing.
  • Context: Added the invoice details, the overdue period, and the relationship status in brackets, because the model can't write a specific email without them. Delete anything that doesn't apply.
  • Task: Reduced your draft to one action, writing the follow-up email, and added "confirm a payment date" because a reminder without a next step rarely gets a reply.
  • Constraints: Replaced "be polite" with testable limits on word count, banned phrases, required details, and one call to action, so you can check the result quickly.
  • Output format: Specified subject line, body, and sign-off so you can paste the result straight into your email client.

3. Gaps

  • Tell me whether this is the first reminder or a later one, and whether your payment terms allow a late fee. Either would change how firm the email should be.
Generated from this prompt by AI. Your results will vary.

Tips and common edits

Use when a prompt keeps giving vague answers. Paste the rough draft where the variable is, then run the upgraded version in a fresh chat to compare.

Questions about this prompt

More in ChatGPT
Trending

Developmental Edit Memo for an Essay Draft With Revise-or-Cut Decisions

Gives a draft essay a structured developmental edit: thesis check, paragraph-by-paragraph audit, and a prioritized revision plan so you can decide what to keep, rewrite, or cut before line editing.

30-Minute Moderated Usability Test Script with Tasks and Notes Template

Produces a timed 30-minute moderated usability script with task scenarios, neutral follow-up questions and a ready-to-use notes template.

4-Week Small Business Launch Plan: $0 and Small-Budget Versions

Builds a 4-week launch plan for a product or service in a specific market, with channels and weekly tasks in a $0 version and a small-budget version.

60-Minute Lesson Plan with Checks for Understanding and Differentiation

Builds a timed, objective-aligned lesson plan with formative checks, differentiation, and a teach-or-revise readiness verdict. It asks for missing inputs first and keeps assumptions separate.

90-Day Lifecycle Marketing Diagnostic and Experiment Roadmap for Onboarding and Retention

Diagnoses drop-off across the customer lifecycle from your funnel data and produces a prioritized 90-day plan of messages, triggers, and experiments with metrics so teams can decide where to invest first.

Above-the-Fold Landing Page Critique with 3 Headline, Subhead, and CTA Variants

Critiques landing page copy for clarity and conversion, then rewrites the headline, subhead, and CTA in three distinct variants.

Adaptive Quiz from My Notes with Weak-Spot Summary

Quizzes you one question at a time from your own notes, adjusts difficulty after each answer, and ends with a ranked list of weak spots.

AI Paper Explainer with Evidence Table and Practical Takeaways

Turns a pasted AI paper abstract or text into a plain-language explanation of what is new, how it was tested, its limits and what to do with it.

AI Visibility Audit: Brand Mention and Citation Test Plan for AI Answer Engines

Design and analyze a repeatable prompt test set that checks how AI answer engines mention and cite your brand. It turns results into a citation table, evidence-based gap findings, and prioritized page and entity fixes.

AI Visibility Prompt Tracker List: 25 Buyer Prompts by Funnel Stage

Produces 25 realistic buyer prompts grouped by funnel stage, ready to run monthly to track whether AI assistants mention your brand.

Anki Flashcards from Lecture Notes as Import-Ready CSV

Turns pasted lecture notes into atomic question-and-answer cards in a CSV that imports directly into Anki.

Architecture Decision Record for a Technology Choice

Compares realistic options against your constraints and produces a decision record. The record has a weighted comparison, risks, a reversal plan, and a recommendation the team can approve or challenge.