Skip to content
How I AIHow I AI

How this PM uses AI for PRDs, JIRA tickets, and replying to coworkers | Dennis Yang (Chime)

Dennis Yang is the Principal Product Manager for Generative AI at Chime, where he’s pioneered AI workflows that meaningfully increase productivity. While most people use Cursor as a coding tool, Dennis has turned it into a comprehensive product-management system that automates PRD creation, documentation management, ticket creation, status reporting, and even comment responses—without writing code. In this episode, he shares his end-to-end workflow and how non-technical professionals can leverage AI-powered IDEs. *What you’ll learn:* 1. Why Cursor is the perfect hub for product management (even if you don’t code) 2. How to use MCPs (Model Context Protocols) to push content between Cursor, Confluence, and Notion 3. The workflow for creating PRDs in Cursor and automatically responding to comments 4. How to automate Jira ticket creation directly from your PRDs 5. A system for generating comprehensive status reports without manual work 6. How to prototype AI products in minutes using Cursor as a “super MVP” environment 7. Why source-controlled markdown files might replace traditional SaaS tools *Brought to you by:* Zapier—The most connected AI orchestration platform: https://try.zapier.com/howiai Brex—The intelligent finance platform built for founders: https://brex.com/howiai *Where to find Dennis Yang:* Twitter/X: https://twitter.com/sinned LinkedIn: https://www.linkedin.com/in/dennisyang/ Chime: https://www.chime.com/ *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo *In this episode, we cover:* (00:00) Introduction to Dennis Yang (03:00) Why Cursor is ideal for product management workflows (04:53) Setting up Cursor for non-coding use cases with markdown preview (09:35) Creating PRDs in Cursor and using source control for documentation (10:33) Using MCPs to publish content to Confluence and Notion (11:38) Bridging the gap between engineering and product (17:00) Reading and responding to document comments with AI assistance (21:37) Creating comprehensive Jira tickets directly from PRDs (25:51) Generating automated status reports from Jira data (30:23) Building a morning briefing system with ChatGPT (35:03) Generating personal morning briefings using ChatGPT (40:04) The “super MVP” approach to AI product development (46:37) Lightning round and final thoughts *Tools referenced:* • Cursor: https://cursor.com/ • Confluence: https://www.atlassian.com/software/confluence • Notion: https://www.notion.so/ • Jira: https://www.atlassian.com/software/jira • ChatGPT: https://chat.openai.com/ • Claude: https://claude.ai/ • Git: https://git-scm.com/ *Other references:* • News API: https://newsapi.org/ • Semrush: https://www.semrush.com/ _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Claire VohostDennis Yangguest
Oct 27, 202550mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

A PM’s Cursor-based AI system for docs, Jira, and updates

  1. Dennis Yang (Principal PM for GenAI at Chime) walks through using Cursor as an AI “hub” for everyday product-management work, emphasizing speed, multi-model access, and tool interoperability via MCPs.
  2. He drafts PRDs in Markdown inside Cursor (with preview), source-controls them with Git, then publishes to Confluence/Notion and links back to the canonical doc for round-trip workflows.
  3. He uses AI to read and triage stakeholder comments, draft replies for human approval, and then post responses as the authenticated user—keeping the PM “in the loop” while removing toil.
  4. Finally, he shows how to generate high-quality Jira epics/stories directly from PRDs, automate weekly status reports from Jira activity, and prototype an agentic “morning briefing” product in a ‘super MVP’ way using tool-calling and model switching inside Cursor.

IDEAS WORTH REMEMBERING

5 ideas

Cursor is valuable to PMs because it combines models, files, and tools.

Dennis prefers Cursor as an AI UI because it supports multiple LLMs, has native access to a local file system for durable artifacts, and connects to key PM systems through MCPs.

Markdown + preview turns an IDE into a practical document editor.

Working in Markdown aligns with LLM strengths, and using a Markdown preview extension makes PRDs readable and shareable without living in Google Docs/Confluence while drafting.

Treat PRDs as versioned artifacts, not static snapshots.

By putting PRDs under Git, PMs get change tracking and can imagine a workflow where docs live adjacent to code—encouraging continuous updates as learning happens during development.

Interoperability becomes a selection criterion for AI workflows.

Both hosts stress that tools that “lock content away” are less useful; the winning systems will let content move fluidly across repos, docs, and task trackers via standardized interfaces like MCP.

Close the collaboration loop: publish, collect comments, respond with AI assistance.

Dennis exports early PRDs to Confluence/Notion for broad commenting, then has AI read comments, prioritize them, draft responses, and (after review) post replies—reducing manual communication overhead.

WORDS WORTH SAVING

5 quotes

The reason why Cursor is my favorite UI for the AI is... it has all the interfaces and interactions and connections into the tools that are critical for my daily product management.

— Dennis Yang

The most useful solutions will have interoperability as one of the key things.

— Dennis Yang

If that's my content, and I want all my systems to be able to access it when it needs to.

— Dennis Yang

Cursor reads the PRD... and then splits the effective tickets. The story tickets in particular are very, very well described.

— Dennis Yang

It's really improving communication and reducing the time I'm spending writing status, and at the same time, improving the status content... up to leadership and across the organization.

— Dennis Yang

Cursor as PM workflow hub (non-coding use)Markdown-first writing + live previewGit/source control for product artifactsMCP interoperability (Jira, Confluence, Notion, Figma, custom APIs)Publishing docs + round-trip linkingAI-assisted comment triage and repliesPRD-to-Jira ticket generation and status automationMorning briefing systems (ChatGPT memory vs tool-based briefings)“Super MVP” agent prototyping inside Cursor

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome