Find the AI agent course that fits where you are.
Seven quick questions about your role, your agents and what is in your way. You get one recording to watch tonight, one live lab and one course.
About two minutes, one tap per question, then your work email.
Your plan
Watch one hour-long build from start to finish before anything else. Every plan below builds on it.
Build an Autonomous Claude Code AgentFor designing the system
- Free tonightBuild an Autonomous Claude Code Agent
The most recent Lightning session, recorded.
Watch the recording - Free, liveBuild a Multi-Agent System with MCP
A planner, an engineer and a reviewer that take one issue from plan to pull request, each with only the tools its role needs.
Save a seat - Pro courseArchitect an agent system with the OpenAI Agents SDK
Lessons: Design the loop, the roles and the board; Engineer the context and memory.
See the Pro courses
For context and memory
- Free tonightBuild an Autonomous Claude Code Agent
The most recent Lightning session, recorded.
Watch the recording - Free, liveCut AI Agent Costs with Token Economics
One agent run priced step by step, rolled up to a cost per feature and per customer, and cut with routing, caching and a budget.
Save a seat - Pro courseArchitect an agent system with the OpenAI Agents SDK
Lessons: Design the loop, the roles and the board; Engineer the context and memory.
See the Pro courses
For tool calling and mcp
- Free tonightBuild an Autonomous Claude Code Agent
The most recent Lightning session, recorded.
Watch the recording - Free, liveBuild a Multi-Agent System with MCP
A planner, an engineer and a reviewer that take one issue from plan to pull request, each with only the tools its role needs.
Save a seat - Pro courseArchitect an agent system with the OpenAI Agents SDK
Lessons: Design the loop, the roles and the board; Engineer the context and memory.
See the Pro courses
For long-running work that survives a crash
- Free tonightBuild an Autonomous Claude Code Agent
The most recent Lightning session, recorded.
Watch the recording - Free, liveBuild an AI Agent Governance Framework
A way to decide which work goes to agents, who approves what they do, and what they changed each month.
Save a seat - Pro courseBuild a team of agents with MCP and Temporal
Lessons: Build a team of agents; Make the work durable.
See the Pro courses
For security
- Free tonightBuild an Autonomous Claude Code Agent
The most recent Lightning session, recorded.
Watch the recording - Free, liveSecure AI Agents with Guardrails
Agents that each sign in with their own identity, act only within the user's permissions and refuse an injected instruction.
Save a seat - Pro courseSecure and deploy agents with Keycloak and LiteLLM
Lessons: Secure every agent and every action; Deploy behind an LLM gateway.
See the Pro courses
For cost, traces and evals
- Free tonightBuild an Autonomous Claude Code Agent
The most recent Lightning session, recorded.
Watch the recording - Free, liveCut AI Agent Costs with Token Economics
One agent run priced step by step, rolled up to a cost per feature and per customer, and cut with routing, caching and a budget.
Save a seat - Pro courseSecure and deploy agents with Keycloak and LiteLLM
Lessons: Secure every agent and every action; Deploy behind an LLM gateway.
See the Pro courses
For rules and approvals
- Free tonightBuild an Autonomous Claude Code Agent
The most recent Lightning session, recorded.
Watch the recording - Free, liveBuild AI Agent Evals from Production Traces
A test set built from real agent runs, scored by code checks and an LLM judge, that fails the build when the agent gets worse.
Save a seat - Pro courseGovern agents with policy as code and signed skills
Lessons: Write the rules as code; Add a role from signed skills.
See the Pro courses
A private lab builds one part of the system on your own repository, with a written follow-up for the manager who has to say yes.
See private labs for teamsTeams learn faster when they build the same system on the same codebase.
See private labs for teamsWhat you get at the end
A sample result: a recording to watch first, the next live lab that fits, and the Pro course for your stage, each with one line on why.
Watch first
Build an Autonomous Claude Code Agent
Claude Code can fix an issue; the hard part is letting it run while you work on something else.
Then build it live
Build a Multi-Agent System with MCP
A planner, an engineer and a reviewer that take one issue from plan to pull request, each with only the tools its role needs.
Then go deeper
Architect an agent system with the OpenAI Agents SDK
Lessons: Design the loop, the roles and the board; Engineer the context and memory.
Why take it
One starting point.
Three picks in order, with no catalogue to scroll.
Matched to your work.
The picks follow your role and what blocks you today.
A live lab on the calendar.
The next lab that fits, with its date.