Skip to main content
Text & code prompt
ChatGPT
Claude
Claude Code
Cursor
DeepSeek
Gemini
GitHub Copilot
Grok
Microsoft Copilot
Mistral Vibe

Write a Clear Task Contract for an AI Coding Agent

Turn a feature request into a task contract for developers in ChatGPT: scope, files to inspect, acceptance checks, validation commands and open questions.

By Genius ForgesUpdated Oct 10, 2026

Make it yours

Fill in the inputs. Your prompt updates as you type.

Your prompt

Turn a feature request into an implementation contract for a coding assistant.
Feature request: {{feature}}
Repository context: {{repository context}}
Constraints: {{constraints}}
Expected user behavior: {{acceptance behavior}}
Produce: objective, in-scope changes, files to inspect, unresolved questions, acceptance checks, validation commands and a rollback approach. Define observable before-and-after behavior. Do not invent file names, dependencies, credentials or test commands absent from the supplied context; mark them as inspect-first. Require the agent to preserve unrelated changes, avoid printing secrets and report actual checks performed. Ask only questions that block meaningful progress.

4 inputs still blank. Empty inputs stay as placeholders when copied.

One email a week

One email a week: new free AI tools, prompts and free-plan changes. No spam, unsubscribe any time.

Example result

Illustrative input Feature: save a published prompt, reload the page, and retrieve it. Draft records must remain unavailable. Reference output / expected behavior Acceptance contract: save by stable slug; fetch published database records; show a missing-resource state; verify reload and unpublished cases. Stop before deployment. Check A happy-path check alone is insufficient; verify removed records and failed requests.

Illustrative example; not tested on the listed platform. Example inputs are included in the response.

How to use this prompt

  1. 1Replace the input fields with your own context.
  2. 2Paste the personalized prompt into a compatible assistant.
  3. 3Check the output against your facts and refine one instruction at a time.

Tips & limitations

The example is an editorial illustration, not a claim of platform-specific testing. Results depend on your inputs and model. Review factual claims before publishing or acting. Compatible platforms were selected from provider documentation; the example has not been re-tested on every platform. Features may require the relevant generation mode or account plan. Quality check: A happy-path check alone is insufficient; verify removed records and failed requests.

Explore collections

agentic codingacceptance criteriaimplementation brief

Did this help you complete your task?

Tell us what needs improving. No account or private output required.

Was this useful?
Report incorrect information or a broken link

Review evidence

Illustrative example · 2026-10-07

Illustrative source inputs and reference outputs, not a recorded model benchmark. The example is an editorial illustration, not a claim of platform-specific testing. Results depend on your inputs and model. Review factual claims before publishing or acting. Compatible platforms were selected from provider documentation; the example has not been re-tested on every platform. Features may require the relevant generation mode or account plan. Quality check: A happy-path check alone is insufficient; verify removed records and failed requests.

Keep creating

Explore the library
ChatGPT

Turn this idea into a daily skill

Practice with a small input and check the result before sharing.

We use optional cookies for analytics and referral tracking. Learn more about our privacy policy