Learning Lab
Master production agent workflows with empirical verification patterns
Safe sandbox for learning and building phased workflow skills with strict validation. Move beyond "LLM writes text" to "LLM executes validated procedures with evidence."
What You'll Learn
Test Harness Pattern
Understand the mental model behind evidence-based LLM workflows
Multi-Phase Orchestration
Build workflows with strict validation gates between phases
Empirical Verification
Use scripts to validate LLM outputs instead of trusting them
Production Deployment
Take your workflows from learning lab to production systems
Guided Learning Paths
Beginner
1 hourGet started with the test harness pattern
Advanced
3 hoursDeep dive into orchestration patterns
Reference
As neededVisual maps and reference documentation
Interactive Jupyter Notebooks
Launch instantly in Google Colab - no local setup required
Agent Skills (5 notebooks)
What is SKILL.md?
Skill Anatomy
Build Your First Skill
Advanced Skill Patterns
Skill Validation
Plugin Development (4 notebooks)
What is a Plugin?
Plugin Structure
Build Your First Plugin
MCP Server Plugins
Orchestration Patterns (2 notebooks)
Mental Model
Orchestration Pattern
Getting Started
Read the Introduction
Start with GUIDE 00: Start Here to understand the mental model (5 min)
Choose Your Path
Pick Beginner, Advanced, or Reference based on your experience level
Try Jupyter Notebooks
Launch interactive tutorials in Google Colab - no setup required
Build Your Own
Adapt the reference implementation for your production use case