Agentic AI Academy
Learn the tools that run AI agents in production. Each course is a short series of lessons: you watch the commands run, then repeat them with the lab files.
The first lesson of every course is free.
kagent 1.0: Run AI Agents on Kubernetes
Install kagent, build a Kubernetes-native agent, give it MCP tools, contain it with egress policies and trace everything it does.
- Agent Substrate sandboxes
- MCP tools
- Egress policies
- OpenTelemetry tracing
Build and Secure an MCP Server
Build a real MCP server in Python with the official SDK, serve it over HTTP, add authentication and hardening, then deploy it to a kagent cluster.
- Typed tools, resources, prompts
- Streamable HTTP
- Authentication
- Deploy to Kubernetes
Run Coding Agents in Production with goose and AGENTS.md
Install goose, teach it your project's rules with AGENTS.md, then run it the way a team does: recipes, CI, guardrails and a record of what it did.
- AGENTS.md
- Recipes
- GitHub Actions
- Guardrails with hooks
A synthetic voice
Every lesson is narrated with a synthetic voice made from the author's own voice. The commands, files and results you see are real: they were run against the exact versions named in each course.
Independent training
This Academy is independent. It is not affiliated with or endorsed by the kagent, Model Context Protocol or goose projects, or by their maintainers.