Product Builder Certification: Build with AI Agents via Spec-Driven Development
GK
3x Founder | ex-Amazon Sr PM (ML)
Vibe coding gets you a demo. Spec engineering gets you a real app.
Use code LAUNCH for $250 off
📌 16,000+ product folks came to my lightning lesson featured by Lenny Rachitsky, where we unpacked their pain with AI.
Vibe-coding works fine in a demo, and then:
🌀 the agent goes in circles
📦 the code it generates is in a black box
❓ and when asked how you knew it works, you have no clear answer.
🛠️ I felt the same pain and built a framework, which this course teaches:
We start with a customer problem and my Spec Kit.
Define what to build, direct AI agents to build, evaluate and ship the solution.
A live build assistant shows what each agent did and why.
Why a course? My one-day workshop teaches the method, but one day is too short to learn a tech stack and ship your build. Three weeks lets you apply each session to your own project:
🧭 learn and practice a framework for building cleanly with AI that works on any project
🧪 evaluate your AI app with Bar Raiser evals
🚀 push it live on GitHub, PostHog, Vercel and Cloudflare, tools real teams use
🧰 learn best practices for Claude Code
🎯 Add a new app to your portfolio and showcase your PM skills.
🏆 Past students took this method into their teams and used it to show hiring managers how they think.
What you’ll learn
Go from a vibe-coded demo to a real app with core PM skills (discovery, specs, evals, launch) while AI agents build from your spec.
Run product discovery with an AI interviewer that sharpens your idea into a problem statement, using Amazon's Working Backwards.
Write a spec, your PRD for AI agents, that they treat as the source of truth, and catch the vague parts before they turn into bugs.
Direct a planner, an initializer and a coder agent, each with one job, handing work to each other cleanly.
Follow what each agent did and why on a live build assistant, so your code never becomes a black box.
Write evals that an independent judge runs against your acceptance criteria, with results you can read.
Find the real cause of a failure with a Deep Dive, make one fix, and show the score moved.
Set up GitHub, PostHog, Vercel and Cloudflare step by step, starting from zero.
Put your app online securely and use product analytics to learn how real users interact with it.
Answer the questions your stakeholders or a hiring manager will ask, first to an agent panel and then live to the cohort.
Earn the certificate on your own project, with feedback from me.
Learn directly from GK
GK
Ex-Amazon Senior PM (ML) | Lenny-featured Lightning Lesson| Top 100 Instructor
Who this course is for
Product managers who have vibe-coded something and want apps that hold up, at work or on their own. No coding background needed.
People moving into an AI product manager or builder role who need a project they can explain from first decision to live product.
Engineers who already ship and want to own what gets built, from the customer problem to the live product.
Prerequisites
A paid Claude plan (Pro or Max)
Every session builds inside Claude Code, which runs on a paid Claude plan.
A laptop where you can install software
Some work laptops block installs, so a personal laptop may be easier.
No coding experience, just a project in mind
Bring an idea for a new app or a feature at work. Session 0 sets up every tool with you before we build.
What's included
Live sessions
Learn directly from GK in a real-time, interactive format.
🎥 12 hours live with me
A Claude Code setup session, four build sessions, two office hours and a demo day. Every session is recorded, so you can catch up if you miss one.
🧰 My Spec Kit, yours to keep
The skills, commands and builder agents behind every session. Use them on your own projects and with your team after the course. No resale or redistribution.
📝 Personal feedback on your capstone
I review your project against your spec and send written feedback before you earn the certificate.
🎁 Bonus: Persuasion factors
A bonus lesson on getting your team to adopt what you build. Details below.
💬 Slack community with past cohorts
Join workshop and course alumni in one Slack to share builds and get feedback, and keep coming to office hours after the course ends.
♾️ Lifetime access
Go back to course content and recordings whenever you need to.
🏆 Product Builder Certification
Earned on your own project, graded against your spec, and ready to share with your employer or on LinkedIn.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Course syllabus
Week 1
Dec
4
Session 0: Get started with Claude Code
Dec
5
Session 1: Working Backwards: start with who the problem is for
Week 2
Dec
9
Office hour 1
Dec
11
Session 2: Building with AI agents: direct the team, track every step live
Dec
12
Session 3: Bar Raiser evals: the skill every AI builder needs now
Free resources
Testimonials
I watched all 21 sessions in the Maven/Lenny Rachitsky "AI-Native Product Manager" Lightning Lesson series.
Most "AI for PMs" content sticks to the obvious: one-shot PRDs, prototyping, market research. Useful, but usually surface-level. What I'm after is how AI fits into the mess. The work that looks different at every company and for every PM.
𝟭. 𝗥𝗮𝗶𝘀𝗲 𝗬𝗼𝘂𝗿 𝗧𝗲𝗰𝗵𝗻𝗶𝗰𝗮𝗹 𝗕𝗮𝗿 𝗮𝘀 𝗮𝗻 𝗔𝗜-𝗡𝗮𝘁𝗶𝘃𝗲 𝗣𝗠 (Gayathri Keerthana Shanmuga Sundaram, Jason P. Yoong)
The best session of all 21. Gayathri goes through fine-tuning a support chatbot agent for Air Canada, focusing on a specific policy area, to keep the evals demo consumable and nuanced. Smart move. Talks about how to use the eval results and how to work with developers on it [...]
Guy Peled
Product ManagerGK was excellent to work with. She supported us across AI workshops and AI course tutoring, and consistently delivered high-quality, well-structured materials and outputs. Communication was clear and proactive, and she genuinely cared about achieving strong outcomes, not just “completing tasks.” She also interacted brilliantly with students and workshop participants: engaging, supportive, and very clear in explanations and facilitation. Everything was delivered on time, with strong attention to detail, and she stayed flexible and responsive as priorities and timelines evolved[...]she’s thoughtful, reliable, and simply a great person to collaborate with. I strongly recommend her for training delivery/support and for helping early-stage startups, especially across AI, marketing, and product
Vitaly
Director at Aon STG | AI & Digital Strategy | Venture BuilderWe were seeking a product owner [...] to help us understand how the ML model can be leveraged to solve concrete business problems and surface actionable insights for business users. This is where Gayathri shone. She laid out and executed a strategy for business application… with simple and easy-to-understand language and used relatable examples… Gayathri's contributions have not only advanced the team's understanding of customer behavior but have also set new benchmarks for how we leverage machine learning in business.
Michael
Principal Applied ScientistGK is a great teacher: so much practical guidance was packed into this short workshop! Nearly the entire class was hands-on, building something real but with enough room to customize it. This approach is fairly different than a lot of similarly positioned courses and I found it the best means to truly learn the material.
Karl
Product Manager · ex-Google
🎁 Persuasion factors: what wins stakeholders over, and why data alone won't
Bonus lesson. Students who took this method to work found the build was the easy part. Getting a team to adopt it was harder.
🧠 What stakeholders actually weigh, and why data ranks behind preparation and listening
🤝 Which parts AI can help you prepare, and which only you can bring
🎯 Pressure-test your rollout pitch against a panel of stakeholder agents before the real meeting
🗓️ Schedule
Sessions run on Fridays and Saturdays at 6pm UK / 1pm ET, with office hours midweek. Everything is recorded. The syllabus above shows this cohort's dates, including any holiday break.
Week 1
🛠️ Friday · Session 0: Get started with Claude Code (1h)
🧭 Saturday · Session 1: Working Backwards: start with who the problem is for (2h)
Week 2
💬 Wednesday · Office hour 1 (1h)
🤖 Friday · Session 2: Building with AI agents: direct the team, track every step live (2h)
✅ Saturday · Session 3: Bar Raiser evals: the skill every AI builder needs now (2h)
Week 3
💬 Thursday · Office hour 2: capstone clinic (1h)
🚀 Friday · Session 4: Put it online safely, and learn from real user interactions (2h)
🎤 Saturday · Demo day: defend your build to a stakeholder or hiring panel (1h)
After the course
♾️ Office hours stay open to you. Alumni keep coming back long after their cohort ends to work through new builds with me and learn from each other.
Frequently asked questions
Maven for Teams
Reimbursement
Get your company to pay
Everything L&D needs: email template, receipts, and certificate of completion.
Get reimbursedTeam discount
Learn with your teammates
Save 20%+ when 2 or more teammates enroll in the same cohort.
Save 20%+ with a teamPrivate cohort
Run a cohort for your org
A dedicated cohort with a custom schedule and curriculum, tailored to your team.
Book a private cohort$990
USD