Product Engineer with AI · 26 weeks · 8–10 hrs / week

PM to Product Engineer

A 26-week, hands-on path from senior product manager to product engineer

Weeks completed: 0/26

Start week 1 Syllabus Domain packs

A 26-week, hands-on path for experienced product managers who want to build, ship and measure real software, and hold their own with software and data engineers.

Who it’s for

Experienced product managers who already know discovery, prioritisation and stakeholders, and want the engineering half: the CLI, git, Python and TypeScript, full-stack apps, data pipelines on Databricks, AI features with evals, and production operations.

It also suits designers, analysts and founders who want to build. No prior coding is assumed, but you’ll need a Mac (or Linux; Windows with WSL works with small changes) and 8–10 hours a week.

What you’ll be able to do

  • Build and ship small products end to end, then measure whether they worked.
  • Follow and contribute to design reviews, PR discussions and pipeline debates.
  • Make sound trade-offs across UI, backend, data and AI, and explain them to executives.
  • Know where your knowledge ends, and say so.

Not the goal: senior-engineer depth, designing large distributed systems alone, or production on-call.

How it works

Each week (8–10 hours):

  1. Concept brief: a short explainer and the vocabulary you’ll hear in standups
  2. Guided lab: exact commands, on your own machine
  3. Unguided challenge: clear acceptance criteria, no hand-holding
  4. Thread items: product, stats, testing, security, frontend, cost, responsible AI
  5. System design every two weeks: a one-page design doc and ADR, defended
  6. Mock reviews every 3–4 weeks: an AI tutor plays a sceptical staff engineer, data engineer or SRE
  7. Check: 5 questions plus 2 recycled for spaced repetition
  8. Teach-back: explain it in your own words

An AI coding assistant is your pair programmer from week 5. For weeks 1–4, you type everything yourself.

The phases

Phase Weeks You ship
0. Workstation 1 A reproducible dev setup in git
1. CLI fluency 2–3 A CLI tool: API → JSON → CSV
2. Git & GitHub 4 CI on every PR
3. Code core 5–8 A typed, tested FastAPI service and TypeScript client
4. Full-stack product 9–11 A deployed Next.js + Postgres app with real users
5. Data engineering & Databricks 12–15 A medallion pipeline deployed from CI, plus a dbt/Dagster comparison
6. AI engineering 16–19 Structured outputs, RAG, an MCP agent with evals in CI, a voice-agent prototype
7. Production 20–22 Containers, tracing, flags, an A/B test, a runbook and a postmortem
Capstone 23–26 One product: discovery → data → AI → shipped → measured → defended

Cross-cutting threads

  • Product discovery & metrics: problem framing, opportunity trees, north-star and guardrail metrics, user research, readouts
  • Stats & experimentation: percentiles, eval statistics, power and sample size, Simpson’s paradox, causal basics
  • Testing & debugging: test pyramid, contract tests, Playwright e2e, debugging drills, light data structures and algorithms
  • Security & compliance: OWASP Top 10, RLS and least privilege, STRIDE, HIPAA and GDPR, incident response
  • Frontend & UX: rendering strategies, accessibility, Core Web Vitals, design tokens
  • Cost & operations: DBUs, token budgets, FinOps, Kubernetes concepts
  • Responsible AI: RAG failure modes, prompt injection, PHI leakage, bias, human-in-the-loop
  • Communication: ADRs, exec summaries, estimation, runbooks, launch memos

Ways of working

One topic a week: product engineers vs PMs, AI-native teams, agent swarms for discovery, continuous discovery, Shape Up, evals-driven development, trunk-based development and DORA, instrumentation-first, Team Topologies, cost-aware building, reading an engineering org, working with data teams, honest estimation, and communicating trade-offs.

Your domain

Every lesson uses one simple running example that anyone can follow: a support-ticket service with tickets, customer accounts, messages and a help centre.

Domain packs let you swap in your own industry from week 12 onwards. Each pack gives you the entity mapping, public datasets, compliance topics and capstone ideas, so the portfolio you finish with is relevant to the work you want to do. Packs cover:

  • Pharma and life sciences: openFDA, FAERS, DailyMed, ClinicalTrials.gov; GxP and Part 11
  • Healthcare: Synthea, FHIR; HIPAA
  • Fintech: PaySim, EDGAR; PCI and KYC
  • E-commerce: Olist, Instacart; GDPR and accessibility law
  • Bring your own: five questions to map any domain

Public or synthetic data only. No real personal data.

Stack

macOS · Homebrew · Ghostty · zsh · mise · uv · pnpm · Docker/OrbStack · git · GitHub Actions · Python · FastAPI · pydantic · TypeScript · zod · Next.js · Postgres (Supabase) · Drizzle · Playwright · DuckDB · Databricks (Delta, Unity Catalog, Lakeflow, Bundles) · dbt · Dagster · Kafka/Redpanda · Claude API · MCP · pgvector · whisper.cpp · OpenTelemetry · Jaeger · OpenTofu · PostHog · Sentry · Vercel

26-week path

Week by week

0. Workstation

Week 01

Workstation

A dotfiles repo with an idempotent bootstrap script

1. CLI fluency

Week 02

CLI Fluency I — Files, Pipes and Text

A log-analysis one-liner toolkit and a cheat sheet
Week 03

CLI Fluency II — Processes, Environment and Scripting

A CLI tool: API → JSON transform → CSV

2. Git & GitHub

Week 04
Mock review

Git and GitHub

CI pipeline that lints and tests every PR

3. Code core

Week 05
System design

Python Core and Your First API

A typed FastAPI service skeleton with an ADR
Week 06

Persistence, Testing and Big-O

The ticket service backed by a real database, with a layered test suite
Week 07
System design

TypeScript and Async

A typed TypeScript client and CLI for the ticket service
Week 08
Mock review

Reading, Refactoring and Contract Tests

A merged (or submitted) open-source PR and contract tests between service and client

4. Full-stack product

Week 09
System design

Full-Stack Foundations — Next.js and Postgres

A Next.js app reading and writing Postgres, running locally, plus a product brief
Week 10

Auth, Deploy, Accessibility and Security

FollowUp deployed with auth, accessible, and security-reviewed; 5 user conversations done
Week 11
System designMock review

Ship to Real Users

FollowUp v1 in the hands of 5+ real users, with e2e tests and RLS

5. Data engineering & Databricks

Week 12

SQL and Data Modelling

A star-schema model of synthetic support data in DuckDB with an analysis notebook
Week 13
System design

Databricks Foundations

Support data loaded into Unity Catalog Delta tables with governance controls and a scheduled job
Week 14

Pipelines, Orchestration and Streaming

A bronze → silver → gold declarative pipeline fed by incremental file drops, plus a local Kafka demo
Week 15
System designMock review

Data Quality, Contracts, Cost and Portability

The pipeline deployed from CI with Bundles, plus a dbt/Dagster rebuild of one gold table

6. AI engineering

Week 16

LLM APIs and Structured Outputs

A support-conversation triage service that returns validated structured output via an API endpoint
Week 17
System design

Retrieval-Augmented Generation

A cited Q&A over a help-centre and policy knowledge base, with a retrieval test set
Week 18

Agents, MCP and Evals

An MCP server plus an agent with an eval suite gating CI, and a red-team report
Week 19
System designMock review

Voice Pipelines and AI System Design

A local voice-agent prototype with a measured latency budget and a launch-review pack

7. Production

Week 20

Containers, Infrastructure and Observability

The ticket service containerised, traced end to end, with infra as code and an experiment plan
Week 21
System design

Feature Flags, Rollouts, Debugging and Threat Modelling

FollowUp with flags and staged rollout, a STRIDE threat model, and a debugging-drill log
Week 22
Mock review

Experiments, Incidents and Runbooks

An A/B test readout, a runbook, and a postmortem from a simulated incident

Capstone

Week 23
System design

Capstone I — Discovery and Architecture

A capstone brief, architecture design doc and shaped build plan
Week 24

Capstone II — Data and Backend

Capstone data pipeline and API running in CI and deployed to a dev environment
Week 25

Capstone III — AI Feature and Frontend

Capstone AI feature gated by evals, a usable accessible UI, instrumentation and flags
Week 26
Mock review

Capstone IV — Ship, Measure, Defend

Capstone live with pilot users, measured, defended, and written up publicly