Agentic AI Bootcamp
Multi-agent systems that plan, coordinate and run in production.
Agentic AI Bootcamp is a 12-week live online bootcamp, taught on Zoom by one instructor at about 15 hours a week, with 6 deployed projects and a one-to-one every week. The founding price is A$200, down from A$400. Live sessions run on weekday evenings from 5:30 PM Sri Lanka and India time, with full-day sessions at weekends.
- Week 1Tool Calling LabA Python script where Claude calls two typed tools and handles their errors
- Weeks 1–2One agent, done properlyA single agent that completes a bounded task reliably, deployed with traces
- Week 3Handoff PrototypeA planner and worker pair that pass a task through a shared JSON state file
- Weeks 3–4CoordinationA two-agent system that splits and merges work, deployed
- Weeks 5–6Protocols and toolsAn MCP server and the agents that use it, deployed
- Week 7Trajectory LoggerA tracing module that records every agent step, tool call and token count to a file
- Weeks 7–8Evaluating agentsAn agent eval suite with trajectories, budgets and adversarial cases, in CI
- Week 9Scheduled Agent RunA Docker container that runs one agent on a cron schedule and posts a summary
- Weeks 9–10FleetsThe capstone: an agent fleet doing real work on a schedule, monitored
- Weeks 11–12Employer brief and hiring sprintThe employer brief shipped, and demo day
- weeks, live on Zoom
- 12
- hours a week
- 15
- projects to build
- 10
- minutes 1-1, every week
- 30
Who it is for, and what you receive.
Engineers who have built at least one LLM application and want to build systems of agents that do real work unattended.
You have built at least one LLM application; Python and Git.
- 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 parts.
Each part teaches for a week, then you build and deploy a project, then a gate checks it before the next part opens. The project and its gate are the part's entry on your record.
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.
- Key skillsAgent loops, tools and stateStructured planningFailure handling and retriesWeek 1
One agent, done properly
- Agent loops, tools and state
- Structured planning
- Retries, timeouts, idempotent actions
- Bounded tasks
You build: A reliable single agent
Week 2Project 1: the agent
- Fixed task suites
- Traces
You build: The agent on a 100-case suite, deployed
Project 1 · the gate at week 2One reliable agent
A single agent that completes a bounded task reliably, deployed with traces
You hand in- Deployed agent
- A fixed suite of 100 cases
- Traces
The gate95% completion on the suite.
What you can do by week 12.
Six deployed agent systems, from one agent to a fleet, and an eval method with budgets that most teams do not have.
- 1
Build a single agent with a bounded task, tools, state and failure handling that completes reliably.
- 2
Design orchestrator and worker patterns with message passing, shared memory, delegation and hand-back.
- 3
Build MCP servers and design tools for agents with permissions, logging and reversibility.
- 4
Evaluate agents by trajectory, step and cost budgets and adversarial cases, in CI.
- 5
Run a fleet of agents with queues, scheduling, backpressure and observability.
- 6
Defend the design of an agent system and its worst hour.
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.
- Week 2Graded, gate signed
One reliable agent
Ninety-five percent task completion on a fixed suite
- Week 4Graded, gate signed
Coordination
The orchestrator recovers from a worker failure without losing the task
- Week 6Graded, gate signed
Protocol and tools
Every tool call is authorised, logged and reversible where it must be
- Week 8Graded, gate signed
Agent evals
A regression in step count or cost fails the build
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. Reserving a spot holds the founding price.
Reserve a seatHow 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.
The whole plan on a few pages: the parts, the projects, the gates and the price. We email it to you.
Get the booklet- 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 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.
Questions people ask.
About Agentic AI Bootcamp, answered from the plan on this page.
- How to Build an AI Agent Loop: From Prompt to Action
- AI Agent Memory: How Agents Remember and Why It Matters
- What is the Model Context Protocol (MCP), and should developers learn it?
- Gen AI Bootcamp · 12-week live bootcamp
- LLM Evals and Reliability Bootcamp · 12-week live bootcamp
- Voice AI Agents Bootcamp · 12-week live bootcamp
One cohort, one instructor. Hold your spot.
A cohort of 25, one instructor, 12 weeks, six things you ship. Spot holders hear the start date first, and nothing is charged before you confirm.
- Six deployed agent systems, from one agent to a fleet
- Agent evals with trajectories and budgets
- A recorded viva
- Your record on /verify
About a minute. No account, no card, and nothing is charged until you confirm.