Module
Module 3 of 4Lesson 4 of 4~13 min

Writing and challenging user stories

User stories written fast but full of gaps get expensive once they reach development, in questions, back-and-forth and rework. This lesson shows how to have AI produce a first draft of stories and acceptance criteria, then challenge it, so you walk into refinement with a backlog already cleared of blind spots.

Lesson objective

By the end of this lesson, you will be able to have user stories and acceptance criteria drafted from a validated opportunity, then have them critiqued (INVEST criteria, edge cases, open questions) before sharing them with the team.

Topics covered

  • user stories
  • acceptance criteria
  • INVEST criteria
  • backlog refinement
  • edge cases

Where it fits

Prompting on your PM deliverables

How do you apply these methods to discovery and delivery without losing fidelity to the data?

Lessons in this module

  1. Turning customer feedback into opportunities
  2. Building a persona grounded in verbatims
  3. Preparing and critiquing an interview guide
  4. Writing and challenging user stories (this lesson)

What you will learn in the course

This lesson is part of the course Prompting for Product Managers: delegate, describe, verify

  • Decide, for a task in your product cycle, whether to hand it to AI, in which mode (automation, augmentation, agent), and what you keep.
  • Explain how an LLM behaves (prediction, dated knowledge, working memory, instruction following) to anticipate its mistakes and pick the right fix.
  • Write a prompt that describes the deliverable, the process and the quality bar, with context, delimited data and examples when needed.
  • Evaluate an AI output (content, process, behavior) against explicit criteria, then improve it through targeted iterations.
  • Produce PM deliverables with AI (feedback synthesis, persona, interview guide, user stories) from real data, and check that they are faithful to it.
  • Configure standing instructions and a dedicated assistant for a recurring task, test it on real cases, and decide when to move to an agent.
  • Apply diligence rules (shared data, transparency, accountability) before using or circulating work produced with AI.