Courses / Live bootcamps
Gen AI Bootcamp
Build and ship LLM products: prompting, retrieval, agents, evals, production.
- 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.
Developers who want to build with language models properly, from the first API call to a monitored product. No machine-learning background needed.
Before you start
Python and Git; no machine-learning background needed.
Skills
- Python
- LLM APIs
- prompt engineering
- RAG
- agents
- MCP
- evals
- observability
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
LLM foundations
Weeks 1 to 2Week 1
LLM foundations
- Tokens, context and sampling
- What models do well and badly
- Prompting with structure, constraints and examples
- The Claude and OpenAI APIs: structured output, caching, batch
You build: A structured-output assistant
Week 2
Project 1: the assistant
- Schema validation
- Test suites on held-out cases
You build: Deployed assistant with a checked schema and tests
Project 1, the gate at week 2
Structured assistant
An assistant that turns messy customer messages into a validated ticket record.
You hand in
- Deployed API
- JSON schema
- Prompt library
- Test suite on a held-out set
The gate
Valid, checked output on the held-out set at the stated rate.
- 2
Retrieval
Weeks 3 to 4Week 3
Retrieval
- Embeddings, vector and hybrid search
- Chunking and metadata
- Reranking
- Grounded generation with citations
- Measuring recall and faithfulness
You build: Ingestion and retrieval over a real corpus
Week 4
Project 2: RAG
- Labelled eval sets
- Citation interfaces
You build: A RAG application with citations, deployed
Project 2, the gate at week 4
RAG over real documents
Answer questions over a 500-page public document set, with citations a reader can check.
You hand in
- Ingestion pipeline
- Hybrid index
- Cited answer interface
- Labelled eval set with recall and faithfulness
The gate
Retrieval precision and faithfulness measured against the labelled set.
- 3
Agents
Weeks 5 to 6Week 5
Agents
- Tool use and function calling
- Control loops, memory, planning
- MCP servers and clients
- Sandboxes and permissions
You build: A single tool-using agent; squads form
Week 6
Project 3: the agent
- Traces
- Completion suites
You build: An agent completing a multi-step task with tools
Project 3, the gate at week 6
Tool-using agent
An agent that researches a company, drafts a brief and files it, using three tools.
You hand in
- Deployed agent
- Tool definitions
- Traces for every run
- Completion suite
The gate
Every tool call and outcome visible in the trace; completion rate reported.
- 4
Evals and safety
Weeks 7 to 8Week 7
Evals and safety
- Golden sets
- LLM-as-judge, calibrated
- Regression suites in CI
- Guardrails, prompt injection, data leakage
You build: Eval harness for projects 1 to 3
Week 8
Project 4: the harness
- Seeded regressions
- Jailbreak suites
You build: The harness in CI, blocking a bad change
Project 4, the gate at week 8
Eval harness
Make projects 1 to 3 safe to change.
You hand in
- Golden sets
- Calibrated judge
- Regression suite in CI
- Guardrail tests
The gate
A seeded regression fails the build; a jailbreak attempt is caught.
- 5
Production
Weeks 9 to 10Week 9
Production
- Serving, latency and cost
- Tracing and dashboards
- Incident review
- Fine-tuning versus prompting
You build: Capstone design
Week 10
Project 5 and the viva
- The capstone in production
- Defending the design on camera
You build: A monitored, costed LLM product; the viva
Project 5, the gate at week 10
Capstone
A production LLM product of your choice, monitored and costed.
You hand in
- Deployed product
- Tracing and dashboard
- Cost model
- Incident runbook
The gate
The viva: defend the design and what breaks at ten times the load.
- 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 LLM product 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 real problem from a hiring partner.
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 deployed LLM applications that cover the whole surface an AI engineering interview asks about, an eval harness you will reuse on every future project, and a recorded viva on a production system.
- 1
Explain how language models produce output well enough to predict where they fail.
- 2
Build an assistant on the Claude and OpenAI APIs with structured output, tool use, streaming and caching, and test it.
- 3
Build a retrieval-augmented application over a real document set and measure retrieval quality and answer faithfulness.
- 4
Build an agent that completes multi-step tasks with tools, with traces for every call.
- 5
Write an eval harness with LLM judges and regression suites that runs in CI and catches a bad prompt change.
- 6
Ship an LLM product with observability, a cost model and an incident process.
Roles this prepares you for
- AI engineer
- LLM engineer
- Applied AI engineer
- ML engineer (LLM)
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, Gen AI Bootcamp
Example
- Week 2Graded, gate signed
Structured assistant
The assistant returns valid, checked output on a held-out set
- Week 4Graded, gate signed
RAG over real documents
Retrieval precision and answer faithfulness measured against a labelled set
- Week 6Graded, gate signed
Tool-using agent
The agent's traces show every tool call and its outcome
- Week 8Graded, gate signed
Eval harness
A regression fails the build; a jailbreak attempt is caught
- Week 10Graded, gate signed
Capstone
A viva: defend the capstone's design and what breaks at ten times the load
- 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.