Dev Guides
Each guide pairs a written lesson with hands-on labs that fail on purpose, an anchored assessment and the material to teach it to a room. Companion videos and short clips accompany the guides that have them.
AI-generated illustrationFeatured · Guide 01 · Intermediate
Build a bounded agent loop in TypeScript, break it with seeded faults, and repair it so the system of record, not the model's message, decides success.
Browse the library
Filter by skill, level and format. Guides list only what they include.
2 of 4 guides
Clear 3 filters
Guide 03IntermediateSecurity and containment
Put the limits on what an agent can reach in code it cannot talk its way past, then prove each limit holds with allow and deny tests.
Guide 04IntermediateMCP and integrations
Put company services behind one version-pinned MCP server that several AI clients share, prove it refuses the wrong callers, and debug it from the bytes up.
How every guide is built
Every lab is executed before publishing, with exact versions, commands and outputs recorded.
Each guide includes a seeded failure, its symptom, the diagnosis and how to verify the fix.
Objectives map to a practical task and an anchored rubric, not a recall quiz.
An instructor kit covers run of show, 12 and 100 learner formats, dry runs and clearance.