Ship with AI — Developer Fast-Track
A hands-on short course for working developers who want to use AI assistants like a senior engineer — specifying, reviewing and verifying instead of pasting and praying. Four evenings-and-weekends weeks, built around your own codebase.
- Duration
- 4 weeks
- Commitment
- ~5 hrs/week · evenings + Saturday labs
- Format
- Live online
- Level
- For people who already write code
Short course
Indicative · your local currency · pre-VAT-determination
Evening + Saturday cohort
Starts 20 September 2026
Reserve a seat — our team follows up by email to arrange payment.
Refund & deferral policyWhat you'll learn
- Spec-driven development — driving AI coding agents with specs, not vibes
- Context engineering and project memory files (CLAUDE.md / AGENTS.md-style) for your codebase
- The agent loop: reviewing and verifying AI-written code so bugs don't ship
- AI-assisted testing, refactoring and debugging on real, messy codebases
- Building small tools and agent automations fast
The AI classes in this program
Every Lightspace program teaches the AI-native method — not a bolt-on module, but a working style woven through the projects.
- Spec-driven development — the discipline of specifying before generating
- Context engineering and project memory files for your own codebase
- The agent loop: specify → generate → review → verify, until it's habit
- Agent automations — delegating whole tasks with guardrails
The curriculum
- 1
Spec-driven development
Week 1Turning intent into good specs and getting AI agents to produce code you'd actually merge.
- 2
The agent loop: review & verify
Week 2Reading AI output critically, testing it, and catching the failure modes before they ship.
- 3
Context engineering
Week 3Project memory and conventions files, structuring context so agents work well on real, messy codebases — refactoring and debugging with control.
- 4
Automate with agents
Week 4Building small internal tools and agent automations that pay for the course in a week.
What you leave with
- A faster, safer AI-native workflow on your own projects
- Habits that keep quality up as speed goes up
- A set of reusable specs, context files and patterns for your stack
How you're taught
Live cohorts led by working practitioners — not pre-recorded videos.
Live, not recorded
Real classes on a schedule, with a group that keeps you moving.
Practitioner instructors
Taught by people who build and ship software for a living.
Feedback on your work
Code review and honest feedback on real projects, every week.
Questions
Where does it take place?
Live online — you can join from anywhere in the world.
How much time does it take?
4 weeks, at roughly ~5 hrs/week · evenings + Saturday labs.
What do I need to start?
For people who already write code.
How do payments work?
There's no payment on this website. You reserve a seat and our team emails you to confirm it and arrange payment.
What language is it taught in?
All live classes and materials are in English.
Full details in our Refund, withdrawal & deferral policy.