The Product Builder Certification: From Vibe Coding to Spec Engineering

4.6 (8)

Gayathri Keerthana (GK)

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

Vibe-coding gets you a prototype; Spec Engineering gives a production-grade app

Last week to enroll: use code LAST15 for 15% off

There's a new role forming in every team - Product Builder - who can ship in short sprints with the customer at the center. 15,900+ professionals came for my free lesson where I showed a primer for this.

My audience surveys show that people use Claude Code or Codex every day, but more than half rate their grip on the craft underneath it at 3 out of 10 or lower.

Spec Engineering, experimented by Anthropic, is meant to fix this.

In this workshop, practice a spec-driven build on a real problem:

🧩 Plan: the agent interviews you and works backwards from a refined problem statement into a spec the it can build from

🤖 Build: watch it decompose the spec into tasks and build cleanly handoffs that survive across sessions.

🔍 Eval: learn the most-wanted PM skills - evals & error analysis; spot the AI slop in your output and fix patterns via a simple, interactive dashboard

👀 The fun part: watch what the agent does across stages on a real-time build assistant.

💼 Get a re-usable and scalable spec kit for future builds.

Students using this kit on their projects have been able to exhibit their product judgement and building skills cleanly to hiring teams.

What you’ll learn

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

Understand what you're building via an interactive LIVE BUILD ASSISTANT that reads what the coding agent does across sessions.
Create your own assistants and dashboards that highlight your product sense to the reviewer.
Run the full loop live on a real problem: 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
You will build a Bar Raiser panel (QA, Security, Architecture) to grade your app, and read traces to catch what automated evals miss.

Give a system for your agent to spot the right layers and make surgical fixes.
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 )