Illia Shapoval

Product Leader, AI practitioner

How to Set Up Context So AI Writes Your Next PRD

Lufthansa Systems

Backbase

Luxoft

UKRSIBBANK BNP Paribas Group

Organise messy reality of a PRD —  Slack, meeting notes, and legal docs into context structured based on your workflow.

Turn scattered decisions into context your AI can use

First - populates the context as you go, second - updates the document based on the decisions made.

Build two skills that write the PRD the way you work (Live)

Walk away with a lean PRD template that I use to align marketing, architecture, legal and C-suite.

Use a lean PRD that actually aligns stakeholders

Walk in with a problem. Walk out with a working prototype.

AI PM @Google - [Bay Area In Person]

Dr. Marily Nika

AI Product Lead @ Google, ex-Meta, Harvard Business School Fellow

athens in person - beginner

July virtual spanish

In 4 hours, you will research a real user problem, write a PRD that survives three senior reviewers, and build a working prototype -- without writing a single line of code yourself.This is not a lecture. You build the entire time.<h3>🗓️ Upcoming Cohorts</h3><ul><li>May 11 | 💻 Zoom Remote<ul><li>Lead: Marily | [101]</li></ul></li><li>May 16 | ☕ Seattle (In-person + Zoom)<ul><li>Lead: Diego | [ADVANCED]</li></ul></li><li>June | 🏛️ Athens (In-person + Zoom)<ul><li>Lead: Marily | [101] | Language: Greek</li></ul></li><li>July 17 | 💻 Virtual Only<ul><li>Lead: Diego | [101] | Language: Spanish / En Español</li></ul></li><li>July 21 | 💻 Virtual Only<ul><li>[ADVANCED]</li></ul></li><li>August 21 | 🏙️ Mountain View (In-person + Zoom)<ul><li>Lead: Marily | [101]</li></ul></li></ul>We will do this in-person but you can also join via zoom from anywhere!By the end of this session, you will have four real artifacts on your laptop:<ol><li>User research backed by real complaints from real people</li><li>A PRD with sections filled from actual evidence</li><li>A working prototype running in your browser with real UI, real sample data, and enough polish to show your stakeholders on Monday</li></ol>You also keep a GitHub repo with reusable templates and tools that work on any project, not just the workshop example.

Learning the right tool for the job

PMs who want to move faster You use AI but haven't made it part of your daily workflow. Leave with reusable tools for PRDs, and reports.

PMs who want to prototype You have ideas but depend on engineering to see them built. Leave with a working prototype you built yourself.

Founders and builders Evaluating whether a problem is worth solving. Leave with user evidence, a PRD, and a prototype to make the call.

Go from using AI as a generic chatbot to your own AI system that knows your work, saves you real time, and comes with ready-made Skills.

Ex-Google Director, Founder AI Over 50

Google

Ancestry

Brett Bouchard

Ex-Google Director, 20+ yrs in tech, Founder of AI Over 50

Cohort 1

AI only gets useful once it knows you. Your decades of experience are exactly what make that work, because good context is really just judgment, and you have plenty of it.You chat with AI, and it still feels generic. The answers come back bland, the advice out there is rarely written for experienced people like you, and you keep re-explaining yourself and redoing the same work. And AI keeps changing every month, which makes now the right time to create a setup that doesn't go stale.In live, hands-on sessions, you'll set up your own AI system. Before without a system: a generic AI writes you a stiff client note you fix for 15 minutes, nods along with whatever you decide, and leaves you rewriting one update for every channel. After with your own system: it writes that note in your voice in 2 minutes, pushes back like a skeptic and catches what you missed, and turns one update into all your channels at once.You'll learn it from someone who lives on it. I spent 20+ years in tech, including time at Google, and I use these same AI systems every day to run my own solo business. Designed for experienced people over 50, peer to peer, with no hype and no condescension.

Set up your own AI system and make your decades of experience the edge

Set up an AI that knows you, so you stop getting generic answers

Turn your recurring work into reusable Skills

Run your AI as a system, not a pile of one-off chats

Get sharper answers and question what AI gives you

Turn your AI into a critic that strengthens your thinking

Get unstuck fast with live help and a group at your level

A senior professional who wants AI to save real time and sharpen their work, without learning to code.

A solo consultant, coach or business owner building their next chapter who wants an AI setup they control.

Someone semi-retired or working flexibly who wants to use AI on their own terms, for the projects and interests that still matter.

Walk in unsure about AI. Walk out with a working AI chief of staff that knows your business and a skill you can show your team.

Director of Product AI at AgVend

Patrick Walther

Director of Product AI at AgVend.

Upstream Ag Insights

Shane Thomas

Runs Upstream Ag Insights, the must-read newsletter for North American ag. Ten y

You have read the books, sat through the summits, and you still cannot answer your board when they ask what you are actually doing about AI. Most leaders use AI like a smarter Google: open a chat, get an answer, close the tab, and the next day it has forgotten them. The good output gets buried in a thread you never reopen. Nothing flows back.This course fixes the shape. You write your context down in your own files: your accounts, your manufacturer programs, your goals, your team. The AI reads them every conversation and starts briefing you like your best EA, surfacing the next call before you ask. It lives on your machine, so it survives a model change and a job change.Knowledge work is shifting from doing the work to directing it. The leaders who practice that now, while the stakes are low, get an enormous head start. In four mornings you build a working system and a custom skill you can show your team on Monday.

Build an AI chief of staff that knows your business, in four mornings.

An AI that briefs you like your best EA, on your own machine

Your Constitution, Business context, and Goals captured in files

A custom skill that automates 30 minutes of your weekly job

A repeatable method you can hand to your leadership team

Ag-tech operators, analysts and investors across the upstream world who want a system that turns scattered context into a daily edge.

Manufacturer and input leaders who want AI that carries their channel and market context.

Ag retail and co-op leaders, from CEO to VP, who run on relationships and want AI that knows their accounts and manufacturer programs.

Be the PM who ships fast and doesn't produce slop.

Staff PM @ Meta | Wharton | Builder

Electronic Arts

Scher Rafay

Staff PM @ Meta | Ship AI to 1.7B DAU | Wharton

August '26 Cohort

<blockquote>You wrote the spec four weeks ago. Your engineer "kind of" built it. Your skip-level wants a quick sync. It's now Tuesday and you're still six alignment meetings away from shipping.You've tried the obvious moves to use AI. But the work takes the same time. Becoming an AI-Native PM, and actually seeing the benefits, requires you to rethink the process.This workshop teaches the PM job differently:<ul><li>Write a PRD in 10 minutes, sometimes after you've already built the prototype</li><li>Synthesize 30 user interviews in an afternoon</li><li>Generate 20 UX variations of an idea, and pick one with conviction</li><li>Design evals without an ML team holding your hand</li><li>Simulate your exec team's objections before the review, not in the room</li><li>Build prototypes when writing a spec is slower than building</li><li>Avoid AI tells in your work so it reads as yours</li></ul>Generate fast with AI, judge well, ship work that's good. Speed is the upgrade. Taste is still your job.Bigger payoff: shorter days, agents handling what you hate, more time on the work that drew you to product management.I built this workflow at Meta and taught dozens of PM workshops internally. This isn't another "become an AI PM" course. This teaches you the job, better, with AI.</blockquote>

Move from spec-and-wait to ship-and-iterate, with AI doing the heavy lifting and your taste running the show. 

Diagnose where AI fits in your PM workflow, and where it doesn't

Write PRDs in 10 minutes (sometimes after the prototype)

Synthesize research and generate variations without losing a weekend

Simulate exec reviews and XFN pushback before the meeting, not in the room

Build your own prototype when writing a spec is slower than building

Ship AI work that reads as yours. Avoid the tells, keep the speed and your voice

PMs who feel slow watching indie builders ship with AI on weekends, and want to compress cycles without losing their taste.

<blockquote>PMs at startups whose teams are going AI-native, and need to model what good AI-native PM work looks like.</blockquote>

<blockquote>PMs who don't build themselves anymore, but need to spot the difference between good AI-native work and slop.</blockquote>

Agentic AI

Coding with AI

AI Workflows

Claude Code

OpenClaw

Vibe Coding

AI Evals

AI Transformation

RAG & Search

AI for PMs

AI for Engineers

AI for Designers

AI for Marketers

AI for Founders

Product Sense

Product Discovery

User Research

Prototyping

Growth

Analytics

Tech Foundations

Strategy

Influence

Leadership

Career Growth

Machine Learning

LLM Ops

Context Eng

Security

System Design

Figma

Design Systems

Visual Design

Design Strategy

Automation

Content Marketing

Demand Gen

Go-to-Market

Product Marketing

Positioning

Social Media

Brand

B2B Marketing

SEO & AEO

AI for Leaders

AI Governance

Communication

Management

People Operations

Exec Presence

Storytelling

Goal-setting

Personal Brand

Fundraising

Everyone

Operators

Data Scientists

Business Analysts

User Researchers

Customer Success

Project Managers

HR Professionals

Sales People

Lawyers

Finance

Investors

Real Estate

Educators

Creators

Product managers who drive strategy, development, and launch of products.

Applying AI tools and techniques to professional workflows — assign alongside more specific AI topics.

Building autonomous AI agent systems that take actions, use tools, and orchestrate multi-step workflows.

Identifying opportunities and validating what to build through customer research, experimentation, and prioritization.

Automating professional workflows with AI tools — productivity, operations, and task automation.

Designing and optimizing the context window for LLM applications — prompt structure, memory, and information retrieval.