Courses / Live bootcamps
Claude Code for Engineering Bootcamp
Run an engineering workflow where Claude Code writes, tests and ships under your review.
- weeks, live on Zoom
- 12
- hours a week
- 15
- deployed projects
- 6
- minutes 1-1, every week
- 30
Who it is for, and what you receive.
Working software engineers, any language, who want to run an engineering workflow where Claude Code writes, tests and ships under their review.
Before you start
You already write software; any language.
Skills
- Claude Code
- TypeScript or Python
- testing
- refactoring
- CI/CD
- code review
- MCP
A week, about 15 hours
- Live on Zoom
- 4h
- Recorded lessons and exercises
- 6h
- The project
- 5h
- 1
Six deployed projects
Each graded by Nova against a published rubric and signed off by the instructor at the gate.
- 2
The recorded lessons
The track's lessons and exercises, graded line by line, open for twelve months after the cohort ends.
- 3
Live on Zoom every week
A 90-minute live code review, a 60-minute squad lab, 60 minutes of office hours, and a 30-minute 1-1 with your instructor.
- 4
Your hiring plan
Opened in week 1 and reviewed in every 1-1: target roles, the gap map, the proof list, weekly actions, an interview log, the outcome.
- 5
The record
Every grade and every project with its repository at square1ai.com/u/{handle}, and the recording of your viva, verifiable by any employer.
- 6
The certificate
A credential ID that resolves at square1ai.com/verify to the real completion.
- 7
The hiring sprint
Weeks 11 and 12: CV and portfolio from graded work, applications, mock interviews scored against the role, demo day.
- 8
Nova for twelve weeks
A tutor with every submission of yours in its memory, at 2am as well as in class.
Twelve weeks in six blocks.
Each block teaches for a week, then you build and deploy a project, then a gate checks it before the next block opens. The project and its gate are the block's record entry.
Live time each week on Zoom: a 90-minute class where the instructor reviews real submissions, a 60-minute squad lab, 60 minutes of office hours, and your own 30-minute 1-1. Nothing is lectured live; the recorded lessons do that.
- 1
Driving Claude Code
Weeks 1 to 2Week 1
Driving Claude Code
- Setup, authentication, permissions
- CLAUDE.md and project context
- Tasks, plans and review
- When to trust and when to read
You build: First feature through Claude Code with a review log
Week 2
Project 1: a feature, reviewed
- Explaining every hunk of a diff
- Review logs as evidence
You build: A feature shipped to a real repo entirely through Claude Code
Project 1, the gate at week 2
A feature, reviewed
Ship a real feature to a real repository using only Claude Code, and prove you understood every line.
You hand in
- The merged feature
- CLAUDE.md
- A review log explaining each change in your own words
The gate
Every change in the diff is explained in your own words.
- 2
Codebases you did not write
Weeks 3 to 4Week 3
Codebases you did not write
- Mapping an unfamiliar codebase with an agent
- Tests as the contract
- Safe refactors
- Characterisation tests
You build: Test coverage on a legacy module
Week 4
Project 2: the refactor
- Behaviour-preserving changes
- Coverage as the gate
You build: A refactor of a legacy codebase with tests added first
Project 2, the gate at week 4
The refactor
Take a legacy module you did not write, put it under test, and refactor it without changing behaviour.
You hand in
- Characterisation tests
- The refactor
- Coverage report before and after
The gate
Coverage rises and behaviour is unchanged.
- 3
Agentic workflows
Weeks 5 to 6Week 5
Agentic workflows
- Hooks
- Skills
- Subagents
- MCP tools in the loop
- Parallel work and worktrees
You build: A hook that stops a bad change; squads form
Week 6
Project 3: the team workflow
- Review gates
- Workflow documentation
You build: Hooks, skills and a review gate in use on a repo
Project 3, the gate at week 6
The team workflow
Build the hooks, skills and review gate a team would use, and run a week of work through it.
You hand in
- Hooks and skills in the repo
- A review gate
- Workflow documentation
The gate
A bad change is stopped by the workflow, not by luck.
- 4
Quality
Weeks 7 to 8Week 7
Quality
- Agent-written tests, human-owned assertions
- Security review with an agent
- Performance work with an agent
You build: A security and performance pass
Week 8
Project 4: hardening
- Reproducing findings
- Verifying fixes
You build: Findings found, fixed and verified on a real service
Project 4, the gate at week 8
Hardening
Run a security and performance pass on a real service with the agent, and fix what you find.
You hand in
- Findings with reproductions
- Fixes
- Verification
The gate
Findings are reproduced, fixed and verified.
- 5
Shipping
Weeks 9 to 10Week 9
Shipping
- CI/CD with agents
- Release notes and documentation
- Incident response with an agent beside you
You build: Release pipeline
Week 10
Project 5 and the viva
- Spec to production
- Defending the decisions
You build: A product feature shipped through the full workflow; the viva
Project 5, the gate at week 10
Spec to production
A product feature from a written spec to production through the full workflow.
You hand in
- Spec
- The feature
- CI/CD
- Release notes
- Incident plan
The gate
The viva: defend what the agent did and what you decided.
- 6
Employer brief and hiring sprint
Weeks 11 to 12Week 11
Employer brief
- A real problem from a hiring partner, in squads
- A partner's engineering problem
- Working to someone else's definition of done
You build: The employer brief in progress
Week 12
Hiring sprint
- CV and portfolio built from graded work
- Applications and follow-ups in the hiring plan
- Mock interviews scored against the role
- Demo day
You build: Project 6 delivered; demo day
Project 6, the gate at week 12
Employer brief
A partner's engineering problem.
You hand in
- The brief delivered
- Demo day
The gate
The brief's owner accepts the result.
What you can do by week 12.
Six shipped features and refactors, every one reviewed by you, and a repeatable agentic engineering workflow you can install on any team's repository in a day.
- 1
Set up Claude Code on a real repository with project context that makes the agent better, and drive it through plans, tasks and reviews.
- 2
Map a codebase you did not write with an agent, add tests first, and refactor without changing behaviour.
- 3
Build a team workflow of hooks, skills and subagents that stops a bad change before it lands.
- 4
Run security and performance passes with an agent and verify every finding yourself.
- 5
Ship a feature from spec to production through the full workflow, with CI/CD, release notes and an incident plan.
- 6
Defend what the agent did and what you decided, on camera.
Roles this prepares you for
- Software engineer (AI-assisted)
- Staff engineer
- Developer productivity engineer
- Engineering manager
No placement rate is shown, because there are no graduates to count yet. The roles above are what the projects are built for.
Your record at week 12.
Every exercise and project is graded by Nova against a rubric you can read, and every grade is kept on one page an employer can open and run. This is what the programme writes to it.
- Graded, line by line
- Nova reads every submission against the brief and the rubric and returns a score, what you did well and what to fix.
- Six gates
- A block does not open until the previous project passes its gate. You always know where you are and what is next.
- A weekly 1-1
- Thirty minutes with your instructor, who has already read your code before the call.
- One page an employer can run
- Every grade, project and the viva recording at /verify. An employer opens it, runs the code and watches you defend it.
Record, Claude Code for Engineering Bootcamp
Example
- Week 2Graded, gate signed
A feature, reviewed
Every change in the diff is explained in your own words
- Week 4Graded, gate signed
The refactor
Coverage rises and behaviour is unchanged
- Week 6Graded, gate signed
The team workflow
A bad change is stopped by the workflow, not by luck
- Week 8Graded, gate signed
Hardening
Findings are reproduced, fixed and verified
- Week 10Graded, gate signed
Spec to production
A viva: defend what the agent did and what you decided
- Week 12Graded, gate signed
Employer brief
The brief's owner accepts the result
- Weeks 1 to 12Kept
Twelve 1-1 notes
What your instructor saw in your work each week, and what you agreed to do next.
- Week 12Kept
Your hiring plan and its outcome
Target roles, the gap map, applications, interviews and where you landed.
The entries, not the grades: those are yours to earn. The page lives at /verify and an employer needs no account to open it.
8 entries, twelve weeks. One email when applications open.
How we help you find a job.
The last block is not curriculum. It is the hiring sprint, and the proof you built in the ten weeks before it.
- 1
Your hiring plan, from week 1
Six parts you and your instructor keep: target roles, the gap map from real postings, the proof to send, weekly actions, an interview log, the outcome. Read before every 1-1.
- 2
The hiring sprint
Weeks 11 and 12: CV, portfolio, applications, mock interviews, and demo day in front of hiring partners.
- 3
A record an employer can run
Your six deployed projects and the recorded viva on /verify. An employer opens it, runs the code and watches you defend it.
- 4
The career agent
Paste a real job posting at /career and it maps the role to your graded work and what to do next.
- 5
The roles directory
Every role we prepare people for, what it pays and what it asks, at /roles.
One email when applications open.
Fifty seats, one instructor, twelve weeks. The waitlist hears the date and the price first, and nothing is charged before the cohort exists.