Run a product-management loop from a source-controlled Markdown PRD: publish a collaboration copy, bring comments back into Cursor, create traceable Jira work, and assemble status updates from the records the team actually maintains.
Source episode · 08:00
How Dennis Yang Automates Product Management and Prototypes AI with Cursorwith Claire Vo
Dennis writes a PRD in Cursor, publishes a collaboration copy through the Confluence MCP, reviews suggested replies to comments, creates a Jira epic and stories, and builds a status report from Jira activity.
A traceable PM workflow connecting the canonical PRD, its collaboration page, reviewed feedback, Jira epic and stories, and a source-linked status report.
AI-first code editor
All-in-one workspace
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
5 steps
Create a product-docs directory in Cursor, preview Markdown, and version it with Git. Connect only the MCP servers needed for the current task and confirm the signed-in identity plus its allowed destinations.
Write the PRD in the canonical Markdown file. Before publishing, search the destination for an existing copy, specify whether to create or update, and save the returned page URL in the PRD.
Using the Confluence MCP, search [space name and ID] for a page linked to PRD ID [ID]. If one exists, report it and do not write yet. Otherwise create a collaboration copy titled [title], preserve headings and tables, and return the new URL so it can be added to the canonical Markdown file.
Cursor's AI can even return the URL of the newly created page and add it back to your original Markdown file for easy reference.
Fetch comments from the exact published page. Have Cursor group them without losing author or thread context and draft one response per comment. Select the replies to post, then record accepted decisions in the canonical PRD.
Read unresolved comments on [page URL]. Return each comment with author, thread, quoted text, affected PRD section, proposed response, and whether it requires a product decision. Do not post replies. I will provide the response IDs to send after review.
Search Jira for work already linked to the PRD. Then create or update the named epic and its stories with user value, scope, dependencies, acceptance criteria, and a backlink to the canonical document.
In Jira project [key], search for issues linked to PRD ID [ID]. Show the proposed epic and story changes first. Each story must include its parent epic, user outcome, scope, acceptance criteria, dependencies, and PRD URL. Do not duplicate an existing issue.
Query the epic for the reporting window and build the update from ticket transitions, comments, blockers, and ownership. Include links and call out stale or missing records instead of guessing.
Create a status report for epic [key] covering [start date] through [end date]. Use Jira history and comments. Separate completed work, current work, blockers, decisions, and next actions. Link every issue, name the owner where recorded, flag tickets with stale or missing updates, and do not infer progress that Jira does not show.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building
Design a weekly meta-workflow that analyzes your interactions with your AI assistant to make it smarter. This system learns your writing style from edits, suggests new automations for repetitive tasks, and helps you filter valuable AI techniques from hype.
Create a daily AI workflow that summarizes yesterday's meetings, identifies urgent tasks, and proactively learns internal company terms it doesn't understand. This keeps your AI assistant's knowledge current and highly relevant to your work.
Build a recurring AI task that automatically gathers updates from your calendar, Slack, and notes to suggest weekly priorities and prepare you for upcoming meetings. Start every Monday with a clear, comprehensive plan without the manual effort.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.