The Product Builder Certification: From Vibe Coding to Spec Engineering

4.6 (8)

Gayathri Keerthana (GK)

ex-Amazon Sr. PM (ML), 3x Founder

PMs and engineers are merging into builders. Vibe coding only gets you halfway.

{EARLY BIRD OFFER: Sign up for $320}

"Vibe-coding goes only so far" is the new reality of building with AI.

15,000+ professionals came for my Lenny-featured Lightning Lesson where I showed a primer to fix this.

There's a new role forming in every team - Product Builder - someone who can ship in short sprints with the customer at the center.

The real question is how to engineer a build that holds past mid-build, without wasting millions of tokens on vague vibe-coding.

Spec Engineering fixes this. Anthropic has been publishing on this but hardly anybody talks about it or shows how it will look like in your world.

In this workshop, I'll show you how to do a spec-driven build on a real problem:

🧩 Plan: Working Backwards into a spec the harness can build from.

🤖 Build: lock "done" as a Bar Raiser commit, build one feature at a time with handoffs that survive context resets.

🔍 Evaluate: a sperate agent that catches what self-grading misses, calibrated to your quality bar

🔁 Strip: remove scaffolding as the model improves

💼 Package these into a re-usable and scalable spec kit for future builds.

Walk away with a mental model to build harnesses from first principles that I've used at Amazon scale.

What you’ll learn

Walk out as a Product Builder, closing the loop from customer problem to structured agentic build.

Run the full loop live on a real problem you bring: spec, build, evaluate, fix. You leave with a build that's not black-boxed

Design an agentic interviewer that creates a sharp, solution-free problem statement, then writes the spec every stage builds from.
Perform an ambiguity audit flags any vague mentions before they reach the build.
Build from a spec of decomposed tasks, with handoff artifacts and a clean state any next agent can pick up.

Written in customer language, expanded from a one-line brief, ready to drive a planner/generator/evaluator loop.
Take away a mental model / a fungible spec kit and integrate it into any other repo or spec kit of your choice.

Design evals that are hard for the LLM to game. An independent judge scores it against your acceptance criteria and flags every regression.
Understand why and when to use binary evals and error analysis.
Ground your evals with customer centered test cases

Give a system for your agent to spot the right layers and make surgical fixes. It's what separates a builder from a vibe-coder.
When a new model ships, cut the scaffolding it no longer needs, using traces rather than guesswork
You leave with a first-principles mental model for harness design that outlasts any single model.

Vibe coding stalls beyond prototype. Spec engineering gives long-lived builds the rigor to survive real customers in production.
You understand how long running agents work and the right context is carried across multiple build sessions

Workshop agenda

Develop your own spec kit with skills and commands for each build stage
Public repos don't have your logic baked in. In this workshop, each build stage is encoded into a skill and invoked through a command which you can re-use as your own spec kit, and scale it too.
Spec and harness: Working Backwards from customer problem
Turn a one-sentence problem into a spec your build treats as truth, then run an ambiguity audit that flags undefined terms before the build.
Build it with agents that leave a trail
Agents build feature by feature and log why each exists, so any regression traces to the feature that caused it.
Evaluate: an independent judge runs your evals
Design evals an independent judge runs against your acceptance criteria. It catches what self-review misses, flags regressions, and tells you ship or hold.
Fix with reciepts
You make one change at the named layer, re-run the eval, and prove it worked, instead of sweeping plausible fixes and hoping.
Strip and clinic: keep it lean as models change
Cut the scaffolding a new model no longer needs, with evidence. We close with a live clinic on your own build.
Closes with an unlimited Q&A and onboarding into Slack community
Join the restof the cohort and share success experiments and ideas.
Breaks will be included at the end of each stage of the build
You'll get a 5-10 min break at the end of every hour.

Learn directly from Gayathri

Gayathri Keerthana (GK)

AI Consultant, ex-Amazon Sr PM (ML), 3x Founder

Previously at / Worked with

See all products from Level Up With AI

Who this workshop is for

PMs who are becoming builders, coding fluency doesn't matter
Engineers who want to wear the PM hat, build customer centered products
Vibe-coders who want to build products that don't crumble mid-build and make the token burn worth it

Prerequisites

Claude Code, Cursor or equivalent installed
Paid plan: Claude Pro/Max or Cursor Pro
A small tool or app you want to build
Bring an idea for an internal tool you'd actually use (e.g., a custom builder pulling from your own data sources)
No prior coding experience needed
You don't need to know to read code. Your customer sense and logical reasoning matter more.

What's included

Live sessions

Learn directly from Gayathri Keerthana (GK) in a real-time, interactive format.

Lifetime access

Go back to course content and recordings whenever you need to.

Private Slack community

A dedicated Slack space for your cohort and past alumni. Share builds, get feedback between sessions, post your wins, and stay accountable after the workshop ends.

Certificate of completion

Share your new skills with your employer or on LinkedIn.

Post-workshop office hour

A week after the workshop, come with any and all questions and doubts to discuss at an office hour with GK

Maven Guarantee

Your purchase is backed by the Maven Guarantee.

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 Manager
GK 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 Builder
We 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 Scientist
I have not come across many such product leaders in my 14 years of experience in tech and product management, including a decade at Amazon… That's when I witnessed that she has the acumen to integrate different methodologies into a cohesive strategy… She consistently pushed the operations teams to look beyond immediate hurdles and focus on broader customer behavior trends… Her entrepreneurial spirit, customer obsession, and innovative problem-solving skills will undoubtedly enable her...
Sarah
Principal PMT (Applied Sciences / ML )