Vibe Producting
Build products with AI — for product managers and product-minded builders. Take an idea to a live, secure, instrumented AI product without being a deep engineer. This is not a framework course; it is a shipping course.
Four rungs. Start where you are, finish at Mastery.
Sessions are always 2 hours. The hours are fixed; the calendar flexes — the same level runs daily, alternate-day, evenings, or as an intensive. Prices shown are student prices; professional pricing is on the pricing page.
Idea to a working thing, in one afternoon
Describe a product out loud and watch it become a working prototype in front of you — then see exactly where the AI helps and where a human still has to think.
The AI-assisted building workflow
Spec-first prompting, steering an AI builder, and reading what it wrote well enough to trust it or reject it. You leave with a prototype that runs.
Your first shipped AI product
From prototype to a real MVP with data, auth and an LLM in the loop — deployed to a public URL that other people can actually use.
A live, secure, instrumented AI product
Product thinking, AI-assisted building, deployment, security, and an AI harness of evals, guardrails and observability. Full syllabus below.
What the levels below Mastery cover
Our ladder is a spiral, not a straight line. L0 and L1 are outcome-first: you make something impressive on the first day and no theory gets in the way. L2 is where the foundations genuinely begin. L3 then deliberately re-covers 60–70% of L2 at real depth before going past it — the overlap is a feature, not repetition. You earn the "why" only once you are invested in the "what".
A demo and a guided first build. No theory at all — just a win you can point at.
Bigger builds, same spirit. Concepts appear only where a build actually needs them.
The first real grounding in how and why — taught applied, ending in a project.
Re-covers L2's foundations at full depth, then goes well beyond into advanced work.
"I shipped an app by describing it — today."
See it: Real products built with AI in minutes rather than months.
Make it, guided: Describe an app in plain English to an AI builder (Lovable, Bolt or v0), watch it appear, tweak it, and deploy it to a public URL.
An AI app builder in the browser — nothing to install. No assessment.
Six sessions, six things you built
- Build an app by describing it (Lovable, Bolt) — a simple useful tool
- Add features and iterate with AI — make it do more
- Make it real — add data and a form
- Add AI to your product — an LLM-powered feature
- Ship it — deploy, get a public URL, share it
- Your own mini product, from an idea you choose, plus a showcase
You leave with a live little product that you built with AI. Assessed on completion and the showcase.
L2 · Practitioner — 40 hours, where the foundations begin
The first real grounding — product thinking, AI foundations, the vibe-coding workflow, and building and shipping an MVP with the basics of security.
| Unit | What you learn and build | Sessions | Hours |
|---|---|---|---|
| U1 · Product Thinking Basics | Problem and users, a simple PRD, scoping an MVP, product metrics | 3 | 6 |
| U2 · AI Foundations for Builders | How LLMs work at an applied level, prompting, model choice, cost versus quality | 3 | 6 |
| U3 · Vibe Coding — Building with AI | AI builders and coding tools (Cursor, Claude Code, v0, Bolt, Lovable); building an app; steering and reviewing AI output | 5 | 10 |
| U4 · Making it a Real Product | Data, auth, an LLM-powered feature, UX for AI | 4 | 8 |
| U5 · Ship & Security Basics | Deploy to a public URL, secrets and API keys, a security and safety checklist, an intro to evals | 3 | 6 |
| U6 · Product Project | Ship a small AI product, presented as a product demo | 2 | 4 |
| Total | 20 | 40 |
Project: A shipped, live AI product — idea to MVP to deployed — presented as a product with a metric.
Tools: AI builders (Cursor, Claude Code, v0, Bolt, Lovable) · LLM APIs · a cloud host (Vercel/Netlify) · a managed backend (Supabase/Firebase) · analytics.
Assessment: Continuous labs 25% · product artifacts — PRD, MVP, deploy — 35% · project 40%.
Overlap into L3: U1–U5 are the foundations L3 deepens — it adds AI product security in depth, the full AI harness of evals, guardrails and observability, growth and monetization, agents in products, and a shipped capstone.
120 hours, unit by unit
This is the complete Mastery syllabus — the ceiling of the stream, and what every level below builds toward.
The outcome
You can take a product from idea to a live, secure, instrumented AI application — writing PRDs, building with AI-assisted tooling, deploying it, securing it, and wrapping it in an "AI harness" of evals, guardrails and observability so it holds up in the real world.
How it runs
120 hours · 60 sessions × 2 hours · about 3 months. Prerequisite: Vibe Producting L2, or a placement check. Product sense helps; deep coding is not required. This is the fastest-moving stream we run, so it is rewritten every cohort.
Tools & environment
| Unit | What you learn and build | Sessions | Hours |
|---|---|---|---|
| U1 · Product Thinking for AI | Product discovery and problem framing · what makes a good AI product rather than a feature · PRDs and specs for AI · user research · product metrics and a north star · scoping an AI MVP | 4 | 8 |
| U2 · AI Foundations for Builders | How LLMs and generative AI work at an applied level · the model landscape and how to choose · capabilities, limits, hallucinations · prompt engineering and structured output · cost, latency and quality trade-offs — enough to make real product calls | 4 | 8 |
| U3 · Vibe Coding — Building with AI | AI-assisted development with Cursor, Claude Code, v0, Bolt, Lovable and Replit · the spec-driven "vibe coding" workflow · turning an idea into a working app fast · reading, reviewing and steering AI-generated code · when to trust it and when not to | 7 | 14 |
| U4 · Building the Product | From prototype to MVP · integrating LLM APIs into a product · data, auth and storage on managed backends · UX for AI — streaming, feedback, empty and error states · the AI product stack | 7 | 14 |
| U5 · Deploying & Shipping | Deployment on Vercel, Netlify or cloud · domains, environments and secrets · web versus app-store shipping · CI/CD basics · analytics and product instrumentation · release and iteration loops | 6 | 12 |
| U6 · AI Product Security | Prompt injection and jailbreaks · data privacy (DPDP, GDPR) and PII handling · API-key and secret management · auth, rate limiting and abuse prevention · a safe-deployment checklist · compliance basics for AI products | 6 | 12 |
| U7 · The AI Harness | Evals — LLM-as-judge, test sets, regression suites · guardrails and safety filters · observability and monitoring — traces, logging, cost · prompt and version management · quality, reliability and drift · human-in-the-loop and feedback loops | 7 | 14 |
| U8 · Agents in Products | What agents and multi-agent systems are, and when a product actually needs one · tool use and function calling at the product level · MCP for connecting tools and data · cost, latency and reliability trade-offs — conceptual plus light hands-on, no framework deep-dive | 4 | 8 |
| U9 · Growth, Analytics & Monetization | Product analytics and instrumentation · activation and retention · A/B testing AI features · pricing and payments integration | 5 | 10 |
| U10 · Advanced AI Product Patterns | Voice and multimodal AI products · scaling and cost at volume · reliability patterns · advanced UX for AI | 5 | 10 |
| U11 · Capstone — Ship a Product | Conceive → build → secure → deploy → instrument → ship a real AI product, with a product story and metrics | 5 | 10 |
| Total | 60 | 120 |
The capstone
Ship a real, live AI product. Conceive it with a PRD and a metric, build it with AI-assisted tooling, secure it, deploy it to a public URL, and wrap it in a basic AI harness — evals, logging and at least one guardrail.
You deliver: the live product, a short product document covering the problem, your decisions, the metrics and what you would do next, and a demo. It is judged like a product, not a coding exercise.
How you're assessed
Syllabus is a working draft — hours per unit are indicative and validated by the practitioner who teaches the stream. AI builder tools rotate quickly; the stream is refreshed every cohort.
Who will teach you
Every instructor is currently building in the field they teach — and is certified on our level template before taking a cohort alone. Subject expertise is the entry ticket, not the job.
Practitioners, not lecturers
Every instructor is currently building in the field they teach. If they stop practising, they stop teaching that stream.
Trained on our template
Subject knowledge is the entry ticket, not the job. Every instructor is certified on the CEFTA level template before they take a cohort alone.
Standardized delivery
The same module runs the same way in every centre and every partner campus. That consistency is the product.
Named instructor profiles go up as each cohort's trainer is confirmed — we publish people, not stock photographs. We're hiring practitioner-instructors →
Tell me when the next batch opens
One email when a cohort is published for this stream. Nothing else, ever.
Stop writing specs for other people to build.
Start with the free 3-hour L0 Discover session — take one of your own ideas from a sentence to something that runs.