An intensive 8-hour programme taking engineers from agent fundamentals to deploying production-grade autonomous systems in TypeScript.
8-Hour Intensive
Intermediate–Advanced
TypeScript / Node.js
3 Working Codebases
Learn how AI agents differ from chatbots, implement the ReAct loop, and manage agent state in TypeScript.
Design and register custom tools that connect agents to external APIs, databases, and services using LangGraph.
Build agents that remember user preferences across sessions using a four-tier memory stack with Redis and Pinecone.
Orchestrate specialised multi-agent systems with resilient communication protocols, error handling, and production monitoring.
01
Autonomous agent that queries a knowledge base, checks order status, and escalates complex issues intelligently.
02
Four-tier memory architecture with importance scoring and Pinecone integration — personalised responses across sessions.
03
Researcher → Writer → Reviewer pipeline with up to 2 revision cycles, generating comprehensive reports autonomously.
Real, deployable TypeScript throughout — not Python notebooks or pseudo-code.
Each block builds directly on the last — foundations to multi-agent with zero skill gaps.
ReAct, circuit breakers, vector memory — the exact patterns used in enterprise production.
Working codebases — not exercises. Templates you can adapt to real business problems.
Support agent, memory system, and research pipeline are ready to adapt from day one.
LangChain, LangGraph, Pinecone, Redis, LangSmith — one cohesive stack in a single day.
Core Principle | Start Simple | Specialise | Optimise Memory | Test Thoroughly | Monitor Everything |
|---|---|---|---|---|---|
08:30 | Registration & Environment Setup 30 min — Node.js, TypeScript, API credentials setup |
09:00 | Block 1 — Foundations & Agent Architecture 2 hrs — ReAct pattern, agent loop, state & memory |
11:00 | Break |
11:15 | Block 2 —Tool Integration 1 hr 15 min — Zod, LangGraph, streaming, async tools |
12:30 | Block 3 — Memory Systems 1 hr 30 min — Conversation buffers, Redis, Pinecone |
13:45 | Lunch Break |
14:30 | Block 4 — Multi-Agent & Production Patterns 1 hr 30 min — Orchestration, circuit breakers, observability |
16:00 | Labs — Hands-On Build Time 1 hr 15 min — 3 labs: support agent, memory system, research pipeline |
17:15 | Wrap-Up, Architecture Decisions & Next Steps 15 min — 15 min — Key takeaways & resources |
TypeScript / Node.js
Anthropic Claude SDK
LangChain · LangGraph
Zod
Redis
xLangSmith