Gen AI Leadership Forum · Development Bootcamp
Chatbots answer. Agents act.

AI Agents & Autonomous Systems Bootcamp

Wiring up an LLM call is easy. Shipping a system that uses tools, remembers across sessions, and coordinates other agents is not. Go from agent fundamentals to production-grade autonomous systems in 8 hands-on hours — all in TypeScript. Three working codebases you keep.

Format
8-Hour Intensive
Level
Intermediate–Advanced
Language
TypeScript / Node.js
Deliverables
3 Working Codebases
60–80%
reduction in manual repetitive work
24/7
autonomous continuous operation
3
production codebases to take home
4
learning blocks, zero skill gaps

Four progressive learning blocks

Block 01 · 2 hrs

Foundations & Agent Architecture

Learn how AI agents differ from chatbots, implement the ReAct loop, and manage agent state in TypeScript.

ReAct patternAgent loopState managementMemory optimisation
Block 02 · 1 hr 15 min

Tool Integration

Design and register custom tools that connect agents to external APIs, databases, and services using LangGraph.

Zod validationLangGraphStreamingAsync / parallel tools
Block 03 · 1 hr 30 min

Memory Systems

Build agents that remember user preferences across sessions using a four-tier memory stack with Redis and Pinecone.

Conversation buffersRedisPinecone4-tier memory
Block 04 · 1 hr 30 min

Multi-Agent & Production Patterns

Orchestrate specialised multi-agent systems with resilient communication, error handling, and production monitoring.

Hierarchical / pipeline / peerCircuit breakersObservabilityCost tracking

Three deliverables you leave with

01

Customer Support Agent

Autonomous agent that queries a knowledge base, checks order status, and escalates complex issues intelligently. ~25 min

02

Multi-Tiered Memory System

Four-tier memory architecture with importance scoring and Pinecone integration — personalised responses across sessions. ~25 min

03

Multi-Agent Research System

Researcher → Writer → Reviewer pipeline with up to 2 revision cycles, generating comprehensive reports autonomously. ~25 min

Built differently from day one

01

TypeScript-first

Real, deployable TypeScript throughout — not Python notebooks or pseudo-code.

02

Progressive complexity

Each block builds directly on the last — foundations to multi-agent with zero skill gaps.

03

Real patterns

ReAct, circuit breakers, vector memory — the exact patterns used in enterprise production.

04

3 complete deliverables

Working codebases — not exercises. Templates you can adapt to real business problems.

05

Immediately applicable

Support agent, memory system, and research pipeline are ready to adapt from day one.

06

Full modern stack

LangChain, LangGraph, Pinecone, Redis, LangSmith — one cohesive stack in a single day.

Full day at a glance

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 — Key takeaways & resources.

What you'll work with

Language
TypeScript / Node.js
LLM
Anthropic Claude SDK
Framework
LangChain · LangGraph
Validation
Zod
Session
Redis
Observability
LangSmith

Ship agents that act — not just chat.

Eight hours, four blocks, three production codebases in TypeScript. October 22, 2026 · OTEAcademy Athens.