AI for Product Managers

Building AI Intuition Through Hands-On Examples

🎯 Workshop Goal

Help PMs build AI intuition through hands-on examples, then apply that intuition to your product decisions.

⏱️ Session Flow (60 min)

Section Time What We Cover
Mental Models 10 min Two modes: "Thinking Partner" + "Task Automator"
Live Demo 30 min End-to-end PM workflow: idea → research → PRD → user stories → Jira
Building AI Products 10 min Interface patterns, configuration, context vs concealment
Closing + Q&A 10 min Toolkit summary, next steps

🧠 Mental Models

The Two Modes of AI

The Two Modes (Core Mental Model)

🧠 Thinking Partner

Brainstorms, researches,
structures ideas, challenges assumptions

Interview synthesis, competitive analysis, feature ideation

⚡ Task Automator

Executes across tools:
reads, writes, updates, queries

Pull from SharePoint, update Jira, create ADO work items

The shift: AI isn't just a conversation partner — it's an over eager junior team member with very little common sense and crazy memory that can read, write, and act on your behalf.

🛠️ How to Talk to AI: The CRAFT Framework

Context — Background information the AI needs

Role — Who should the AI be? (analyst, writer, critic)

Ask — The specific request

Format — How you want the output structured

Tone — Voice and style guidelines

Example:

Context: I'm a PM at a retail POS company. We're evaluating whether to add AI-powered inventory recommendations.

Role: Act as a senior product strategist who has shipped AI features at enterprise SaaS companies.

Ask: Identify the top 3 risks of this feature and how to mitigate each.

Format: Bullet points with risk, likelihood, impact, and mitigation for each.

Tone: Direct and practical, no fluff.

Pro Tips:

  • Be specific about what you DON'T want
  • Include examples of good output when possible
  • Iterate — first response is rarely final

🎯 Case Study: GDPVal

GDPVal is OpenAI's benchmark for evaluating how well AI models can answer real-world GDP and economics questions — demonstrating the gap between "can chat about it" vs "can actually do the task."

Click these links during the presentation to show real examples.

📋 PM User Stories: Today vs. With AI

Let's go through 8 common PM workflows or user journeys, see how we transform them with AI and build some intuition.

📊 Product Management User Stories - pre vs post AI

# User Story With AI Tool
1 Research strategy for a new feature — Explore market trends, competitive landscape, best practices AI runs async research across dozens of sources, delivers structured report with citations ChatGPT Deep Research
2 Synthesize customer interviews — Extract themes, contradictions, key quotes Upload transcripts, AI identifies patterns, surfaces contradictions, pulls quotes Claude.ai Projects
3 Generate and refine a PRD — Draft requirements that translate needs into specs AI generates structured PRD, critiques its own output, identifies gaps and risks Claude Desktop
4 Design prototypes from requirements — Turn specs into visual artifacts Describe in natural language, AI generates working UI prototype in minutes Lovable
5 Publish artifacts to team systems — Get PRDs into Confluence, Slack, etc. AI publishes to Confluence, posts to Slack channels — one command Claude Desktop + MCPs
6 Convert PRD into user stories — Break down into work items with acceptance criteria AI extracts stories, writes acceptance criteria, maintains links to source Claude Desktop
7 Triage stakeholder feedback — Process comments, prioritize, formulate responses AI reads comments, categorizes by urgency/theme, helps formulate and post replies Claude Desktop + MCPs
8 Create work items in Jira/ADO — Push approved stories to project management tools AI creates stories with proper fields, epic links, acceptance criteria — directly Claude Desktop + MCPs

⚡ What Are Skills?

A Skill is a way to teach AI how to do something specific and reusable — packaging your expertise into a format the AI can apply automatically.

Open Standard: Skills are emerging as a portable format across LLMs and agent systems (Claude, GPT, Gemini, open-source agents). Write once, use anywhere — your encoded expertise isn't locked to one vendor.

Without Skills With Skills
Re-explain your format each session Format encoded once, applied always
Quality varies by who's prompting Consistent output for everyone
New team members start from scratch Expertise transfers instantly
Key Insight: Skills are how you scale your expertise. Instead of being the bottleneck who "knows how we do things," you encode that knowledge once and any AI applies it for anyone on the team.

📝 Example Skills

  • Interview Synthesis: Your research framework, quote selection criteria, output format
  • PRD Reviewer: Your checklist, common gaps to flag, acceptance criteria standards
  • ADO Story Creator: Your template, field mappings, how to write acceptance criteria
  • Meeting Summarizer: Your format, action item extraction rules, stakeholder summary style

The Skill Creation Pattern

1. Notice you're repeating yourself → "I keep explaining our PRD format" 2. Write it as instructions → Create SKILL.md with your standards 3. Let Claude auto-apply → Consistent output without reminders 4. Iterate based on gaps → Add to the skill when you spot issues

🎬 Live Demo

Idea to Jira (and prototype if you want!) in One Session

IDEA
RESEARCH
INTERVIEWS
PRD
REVIEW
PUBLISH
STORIES
JIRA
Start
ChatGPT
Deep Res.
Claude
Projects
Claude
Desktop
(Optional)
Lovable
Confluence
+ Slack
Claude
Desktop
Jira
MCP
ChatGPT Deep ResearchAsync research
Claude DesktopThinking + orchestrating
Claude.ai ProjectsDocument context
LovableUI prototypes
Confluence MCPPublish pages
Slack MCPPost messages
Jira MCPCreate tickets

📍 Demo Flow: 10 Steps

1

💡 Start with an idea

Kick off deep research for strategy & market fit

ChatGPT Deep Research
2

🎤 Synthesize interviews

Load transcripts, find themes & pain points

Claude.ai Projects
3

📄 Generate PRD

Draft structured requirements from insights

Claude Desktop
4

🎨 Vibe design

Generate visual prototype from the PRD

Lovable
5

🔍 Review PRD

Get a second opinion, identify gaps

Claude Desktop
6

📤 Publish PRD

Push to Confluence, notify via Slack

MCPs
7

✂️ Create stories

Extract user stories with acceptance criteria

Claude Desktop
8

📤 Publish stories

Push stories for stakeholder review

MCPs
9

💬 Triage feedback

Read comments, prioritize, post replies

MCPs
10

🎫 Create Jira tickets

Push approved stories as work items

Jira MCP

Gray cards are optional steps

🔮 The Bigger Picture

This doesn't have to stop here. If you work collaboratively with your dev team:

📋

PM Workflow

  • Strategy research
  • Customer insights
  • PRDs & user stories
  • Stakeholder alignment
Same context
flows forward
💻

Dev Workflow

  • AI coding tools
  • Architecture designs
  • Implementation
  • Testing & deployment

🔗 The thread from "why are we building this?" to "how is it built?" stays intact.

Presenter Notes

Click a slide to see notes...

1 / 14
← → Space to navigate

Keyboard Shortcuts

Next slide or Space
Previous slide
First slide Home
Last slide End
Toggle overview O
Toggle notes N
Toggle fullscreen F
Close this help Esc or ?