Build a RAG System Like a PM
Priyanka Shetty
AI Product Leader & Builder
Why Building a RAG System as a PM Matters
Every PM is being asked to "add AI" to their roadmap. Almost none of them can tell you the difference between a retrieval problem and a generation problem, or explain why their RAG demo works in the sandbox and falls apart in production.
That gap isn't a technical skills gap — it's a product judgment gap. Engineering can build whatever architecture you ask for. The job of the PM is knowing what to ask for, what tradeoffs that choice creates, and how to evaluate whether it's actually working. That's a scoping and judgment problem, and it's learnable the same way any other product skill is: by building it, breaking it, and fixing it yourself.
This workshop exists because most "learn AI" content for PMs stays at the level of concepts and vocabulary. You'll leave able to defend an architecture decision in a room full of engineers — because you'll have made that decision yourself, watched it fail, and rebuilt it.
What you’ll learn
This is a build day, not a lecture day. By the end of the workshop, you won't just understand RAG conceptually — you'll have built one.
Turn "add AI search" into a real spec engineering can build
Know the 3 decisions that make or break a RAG system
Ask sharper questions before you greenlight the build
Spot when fine-tuning or long-context beats RAG
Stop defaulting to RAG because it's trendy
Make the call with logic, not hype
Ship a working RAG pipeline in one day
Work hands-on with embeddings, chunking, and a vector store — no prior coding required
Leave with a working RAG system you built
Explain your tradeoffs to engineering with confidence
Walk into a design review and hold your own
Bring judgment your team hasn't seen yet
Workshop agenda
Framing: RAG for PMs
What RAG actually is, when it's the right call, and what "done" looks like by the end of today.
Build: Your first RAG pipeline
Stand up retrieval and generation end-to-end using a real, public documentation corpus. Pre-work gets you to the starting line — this block is pure build time.
Diagnose and rebuild
Your pipeline will fail somewhere. Learn to tell a retrieval problem from a generation problem, then fix it live.
Apply: The PM decision layer
Chunking strategy, cost/latency tradeoffs, and the architecture calls you'll need to defend in your own design reviews.
Present and wrap
Share what you built, walk away with a production-readiness checklist, and hear what's next if you want to go deeper.
Learn directly from Priyanka
Priyanka Shetty
AI Product Leader (Oracle, S&P Global, Weill Cornell) | AI Strategist & Founder
Who this workshop is for
PMs who keep hearing "add AI" on their roadmap and need to scope it credibly — not just nod along in meetings.
Product leaders who review AI architecture decisions and want enough technical grounding to push back when it matters
PMs building their own AI skill set for their next role — AI Builder, AI PM, or a pivot into AI product work.
What's included
Live sessions
Learn directly from Priyanka Shetty in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Frequently asked questions
Maven for Teams
Reimbursement
Get your company to pay
Everything L&D needs: email template, receipts, and certificate of completion.
Get reimbursedPrivate cohort
Run a cohort for your org
A dedicated cohort with a custom schedule and curriculum, tailored to your team.
Book a private cohort$299
USD
12–3pm EDT