Presentations in This Series
- How LLM Agents Work →Visual deep dive into agent anatomy — the ReAct loop, tool execution, memory management, and prompt assembly.
- Multi-Agent Workflows →Multi-agent coordination and delegation, with examples from LangGraph and the OpenAI Agents SDK.
- Introduction to LangGraph →Interactive slide deck + 10 runnable examples (Python & TypeScript) covering graph-based agent orchestration.
- Agentic Frameworks Guide →Visual guide to the agentic framework landscape — LangGraph, CrewAI, AutoGen, architecture patterns, and how to choose.
- OpenClaw Guide →Deep dive into the open-source gateway connecting AI coding agents to any messaging platform.
- ReAct Math Agent →Browser-based ReAct agent that solves maths problems step-by-step with a local Ollama LLM, visualising the reasoning loop.
- Research Digest Agent →Autonomous research agent that searches the web, reads sources, and produces structured markdown digests (Claude or Ollama).
- Pydantic AI Deep Dive →In-depth visual guide to Pydantic AI — type-safe agents, structured outputs, dependency injection, tools & ModelRetry, streaming, Pydantic Graph, durable execution, MCP, Logfire observability and evals.