Agentic Systems Lab
An executable lab for learning how agentic systems are actually assembled while separating durable architectural ideas from fast-moving SDK syntax.
The core design principle is:
deterministic workflow spine + bounded agentic decisions + objective verification + human authority at consequential boundaries
The curriculum progresses from a local tool loop to routing, parallel fan-out/fan-in, evaluator–optimizer loops, independent verification, delegation and handoffs, persistent state, human gates, budgets, multi-agent orchestration, and protocol-level interoperability.
It also includes hands-on material for LangGraph, OpenAI Agents SDK, PydanticAI, Google ADK, Microsoft Agent Framework, CrewAI, AWS Strands, LlamaIndex Workflows, MCP, and A2A. The default demonstrations are offline and deterministic so the architecture can be studied independently of provider behavior.