Build the AI systems your team keeps talking about.One Live Lab at a time.
Weekly Live Labs on Tuesdays and Saturdays. You watch it built, build it together, then build it on your own code. Every lab starts from a public GitHub repo and ends with something running.
Yearly membership, no monthly plan. Free Lightning sessions on Maven to try first.
- I do30 minParam builds it live
I run one support-triage task as a single agent, as a fixed workflow and as a supervisor with two workers, and show the traces side by side.
- We do48 minTogether, step by step
We instrument all three, count tokens and latency, and break each one on purpose to see how it fails.
- You do42 minOn your own code
You pick a design for a task from your own work, run it, and defend the choice with your numbers.
BuiltA decision table and a measured comparison of two designs for one real task.
Every lab runs the same way
Thirty minutes to five hours, one outcome. The time splits into three parts, and you write code in two of them.
- 1
I do
Param builds the system live, from the public repo, and explains each decision as it is made.
- 2
We do
You build it alongside, step by step, and we stop wherever something breaks.
- 3
You do
You apply it to your own code or data, then show what you built in the room.
Season 1 Live Labs
System design for AI apps first, then the systems teams ask for: evals, MCP, ingestion, browser agents, AI QA, company brain, AI SDR. Each lab starts from a public repo.
- BuildersSystem design
Pick the right architecture: single agent, workflow or multi-agent
A decision table and a measured comparison of two designs for one real task.
2 hours - LeadersTransformation
Write the AI coding playbook for your team
A two-page playbook: where agents may write code, what needs a spec first, and how review changes.
2 hours - BuildersSystem design
Design a production agent from a blank page
A written architecture for one agent: components, failure modes and a cost estimate, reviewed by peers.
3 hours - LeadersBuying AI
Choose AI models and vendors with your own evals
An eval suite built from your own tasks, and a scored comparison of three models on quality and cost.
2 hours - BuildersEvals
Add evals and tracing to an agent
Traces, a dataset built from real failures, and an experiment that proves a prompt change helped.
3 hours - BuildersSystem design
Make agents survive failures with durable workflows
An agent whose runs retry, pause for a human and resume after a crash.
2 hours
Lightning sessions
Free, one hour, on Maven. Watch the recordings, then join the next one live.
- Recording60 min
Design a Software Factory for Your Coding Agents
See what each layer does and which problem it removes from your daily agent work.
Watch the recordingMaven - Recording60 min
Build Your First Software Factory Execution Harness
Give each agent task its own Git worktree that is created, used and removed cleanly.
Watch the recordingMaven - Recording60 min
Build a Claude Code Verification Harness
Reject code automatically before it merges or deploys, when it breaks your engineering rules.
Watch the recordingMaven - Upcoming, free60 min
Build a Claude Code Agent that fixes GitHub Issues
Structure a real issue so a background agent can execute it without you.
Maven
The cohort, for one system in depth
Three weeks on Maven to build a Software Factory for your coding agents, on your own codebase.
AI-Native Software Factory Buildcamp
Build your workflow, your blueprint and your Software Factory, so real issues become verified pull requests on your own codebase.
$1,297$1,997with code FRIENDS700
- Design Your Triage-to-PR Workflow
- Define the Checks and Human Approvals at Each Stage
- Write the Rules, Skills and Commands Your Agents Load
- Add Hooks and Verification Gates
- Decompose Plans and Run Agents in Isolation
- Gate, Retry and Ship Verified Pull Requests
One price for every lab
Pay once a year and come to as many labs as you want. Or pay once, for good.
$149/year
Every Live Lab for twelve months, as many as you want.
- Every Live Lab, live
- Replays and lab repos for every lab
- Build reviews in show-and-tell on GitHub
- Lab Q&A that stays searchable
$399one time
Everything in Yearly, for as long as Live Labs run.
- Everything in Yearly
- Every future season, no renewal
- Early seats for new formats
No monthly plan. Paying for a team? Team seats are $119 each.
Upskill a team, not one engineer
Teams learn faster when they build the same system together and apply it to the same codebase.
Team pass
$119per seat per year, 5 seats or more
Teams who want every engineer in the weekly labs.
- A Yearly membership for every seat
- Seats moved between people as your team changes
- An attendance report each month
Private lab
From $3,499per lab, up to 20 engineers
Teams who want one lab run on their own stack.
- Any lab from the catalogue, run for your team only
- The You do part on your own repository
- A written follow-up with what to fix next
Audit, train, transform
Through KaaS.teamaudit first, then scoped
Leaders who need delivery to change, not only skills.
- A two-day audit of how your team ships with agents
- Labs picked for the gaps the audit finds
- Implementation scoped after the audit
A community in layers
Start free, join when a lab is worth your evening, bring your team when it is worth theirs.
Readers
Free- Top 1% Engineers newsletter
- Lightning session recordings on Maven
- Public lab repos
Members
$149/year- Every Live Lab, live and replayed
- Build reviews in show-and-tell
- Lab Q&A that stays searchable
Lab captains
By invitation- Members who help others during We do
- Review show-and-tell builds
- First to try new labs
Teams
From 5 seats- Seats for the whole team
- Private labs on your codebase
- An attendance report for the manager
“You learn a system by building it, breaking it and fixing it. So that is what every lab does.”
- Former Head of Software Engineering
- 14 years building production software
- Architect of the pivot behind an €11.6M Series A
Questions
What engineers ask before they join.
What is a Live Lab?
A live, hands-on session built on a public GitHub repo. Param builds it first, you build it together, then you apply it to your own code. Labs run from 30 minutes to 5 hours.
When do labs run?
Shorter labs run on Tuesdays at 16:00 UTC, longer ones on Saturdays at 15:00 UTC. Each lab page shows the time in your own timezone.
What if I miss one live?
Members get the replay and the lab repo. The live session is where you get help, so come when you can.
Is there a monthly plan?
No. Yearly is $149 and covers every lab for twelve months. Lifetime is a one-time $399.
How are labs different from the Maven cohort?
The cohort is a three-week buildcamp on one system, the Software Factory for coding agents. Live Labs are single sessions, each on one system, every week.
What are Lightning sessions?
Free one-hour sessions on Maven. They are the easiest way to see how Param teaches before you join.
Can my company pay?
Yes. Team seats, private labs and invoices are on the teams page.
Who owns the code I write?
You do. Labs start from open-source repos under their own licences, and your changes are yours.