Courses / Live bootcamps
Voice AI Agents Bootcamp
Phone and in-app voice agents that hold a conversation and complete a task.
- 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.
Engineers who have built an LLM application and want to build the voice products contact centres, clinics and sales teams are buying.
Before you start
You have built an LLM application; Python and webhooks.
Skills
- Python
- speech APIs
- telephony
- real-time systems
- agents
- evals
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
Speech in and out
Weeks 1 to 2Week 1
Speech in and out
- Speech-to-text and text-to-speech providers
- Streaming
- Latency budgets
- Turn-taking, barge-in, silence
You build: A browser voice loop
Week 2
Project 1: the loop
- Measuring round-trip latency
- Interruption handling
You build: Voice loop under a stated budget
Project 1, the gate at week 2
Voice loop
Talk to an assistant in the browser with no awkward pauses.
You hand in
- Streaming speech-to-text, LLM and text-to-speech loop
- Latency report
The gate
Round-trip latency under the stated budget.
- 2
Telephony
Weeks 3 to 4Week 3
Telephony
- Numbers, SIP, webhooks
- Call state
- Recording and consent
- Handoff to a human
You build: A phone agent
Week 4
Project 2: a number that answers
- Transcription and logging
- Handoff flows
You build: Agent answering a real number
Project 2, the gate at week 4
A number that answers
Answer a phone number, transcribe the call, log it, hand off when asked.
You hand in
- Telephony integration
- Call state
- Consent flow
- Handoff
The gate
A call answered, transcribed and logged end to end.
- 3
Task completion
Weeks 5 to 6Week 5
Task completion
- Tools over the phone
- Confirmation dialogues
- Error recovery
- Structured data from speech
You build: Booking agent; squads form
Week 6
Project 3: booking by phone
- Scripted call sets
- Completion rates
You build: Booking agent completing tasks by phone
Project 3, the gate at week 6
Booking by phone
Book, change and cancel appointments by voice.
You hand in
- Tools
- Confirmation dialogue
- Error recovery
- Structured records
The gate
Task completion rate on a scripted call set.
- 4
Evaluation
Weeks 7 to 8Week 7
Evaluation
- Conversation evals
- Simulated callers
- Safety and compliance
You build: Simulated-caller suite
Week 8
Project 4: the evals
- Regression gates
- Safety suites
You build: Eval suite in CI
Project 4, the gate at week 8
Conversation evals
Know when the agent gets worse.
You hand in
- Simulated callers
- Safety suite
- CI
The gate
Regression in completion or safety fails the build.
- 5
Production
Weeks 9 to 10Week 9
Production
- Concurrency
- Cost per minute
- Monitoring live calls
- A second language
You build: Production design
Week 10
Project 5 and the viva
- The production agent
- Defending the worst call
You build: Production voice agent with monitoring and a cost model; the viva
Project 5, the gate at week 10
Production
Run it for a clinic's front desk.
You hand in
- Concurrency
- Cost per minute
- Live monitoring
- A second language
The gate
The viva: defend the agent and its worst call.
- 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 voice 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 voice 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 voice agents from a browser loop to a production line, and a conversation eval method that tells you when an agent gets worse before a caller does.
- 1
Build a speech-in, speech-out loop inside a conversational latency budget with turn-taking and interruption.
- 2
Answer a real phone number with call state, recording consent and human handoff.
- 3
Complete tasks by voice with tools, confirmation and error recovery.
- 4
Evaluate conversations with simulated callers and safety checks, in CI.
- 5
Run voice agents in production with concurrency, cost per minute, monitoring and more than one language.
- 6
Defend a voice agent and its worst call.
Roles this prepares you for
- Voice AI engineer
- Conversational AI engineer
- AI engineer
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, Voice AI Agents Bootcamp
Example
- Week 2Graded, gate signed
Voice loop
Round-trip latency under a stated budget
- Week 4Graded, gate signed
A number that answers
A call is answered, transcribed and logged end to end
- Week 6Graded, gate signed
Booking by phone
Task completion rate on a scripted call set
- Week 8Graded, gate signed
Conversation evals
Regression in completion or safety fails the build
- Week 10Graded, gate signed
Production
A viva: defend the agent and its worst call
- 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.