AI Agents

9 interactive modules. Free, browser-based.

AL
Module 1
The Agent Loop & State

Loop + state + LLM-OS + workflows-vs-agents decision + harness anatomy.

Start module →
TU
Module 2
Tool Use & Function Calling

Schemas, ACI + anti-patterns, structured outputs, MCP two ways, Skills, attack-surface preview.

Start module →
WF
Module 3
Workflow Patterns

When NOT to use an agent + the five named patterns + subagent topology.

Start module →
RG
Module 4
Retrieval & RAG

Embeddings as coordinates, retrieve-then-generate, chunking, ANN trade, RAG failure modes.

Start module →
CE
Module 5
Context Engineering

Four context failure modes, four fixes, tool-loading strategy, subagents as context isolation.

Start module →
PR
Module 6
Planning & Reflection

Reasoning budget, ReAct + think tool, Reflexion + verifiers, when to retry, when to stop.

Start module →
EV
Module 7
Evals & Diagnostics

Compounding errors, error analysis first, golden cases, pass^k, the four eval failure modes.

Start module →
SC
Module 8
Security & the Lethal Trifecta

Private data + untrusted content + exfiltration vector. Data-flow graphs, structural defenses, capability scoping.

Start module →
CP
Module 9
Capstone — Three Designs

RAG-only vs workflow vs autonomous agent on the same customer-order task. Compared end to end.

Start module →