The builder track: ship production LLM agents — tool use, memory, MCP, and the harness engineering that makes them reliable.
Never written code? You can still start here.
Module 0 opens with 18 lessons of programming from nothing — your first program, variables, loops, functions, reading errors, the terminal, Git and arrays — before any of the LLM Agent Architect material. No prior coding assumed.
AI Foundations — optional basics (free)
Week 0 · 20 lessons
Beyond the chatbox: what AI assistants really are
How the model "thinks" — and why it changes how you ask
The capability map: what AI does brilliantly
The limits: hallucination, freshness, and what never to trust it with
Your first real win: turn a 30-minute task into 3
6 senior modules · 30lessons · capstone & certificate. Upgrade your plan to unlock the advanced tier.
Advanced RAG & Knowledge Systems
5 lessons
Agentic RAG Architectures
Graph RAG & Knowledge Graphs
Get started
Take the free assessment to see your skill level and get a personalised learning plan.
Take AssessmentFeatured Projects
Tool-Using Chatbot
Code Executor Agent
Web Research Agent
About
LLM Agent Architect
20 questions · ~30 minutes
Context is everything: give it what it needs to know
Give it a role and a goal
Constraints and format: define what "good" looks like
Show, don't tell: examples and templates
Iterate like a pro: steer, don't restart
Documents and reports: summarise, extract, and draft better
Spreadsheets and data: Excel formulas, analysis, and charts
Presentations: from blank page to a solid deck
Long, messy input: transcripts, threads, notes, and screenshots
ChatGPT, Claude, Copilot, Gemini: which to reach for, and when
Make smarter decisions: AI as your thinking partner
Chaining steps: multi-part tasks done reliably
Your prompt library: reusable templates that save hours
Staying safe: privacy, accuracy, and company data
Capstone: do a real task end-to-end (graded) → your certificate
Module 0 — Foundations: LLMs, Prompts, Tools & the Agent Toolkit
Week 0 · 23 lessons
What a program is and how to run your first one
Storing values in variables, and why text and numbers behave differently
Making decisions with if, else and comparisons
Storing many values in a list
Looking things up by name with dictionaries
Doing something to every item with loops
Writing your own functions
Reading errors without panic
Finding the mistake in your own code
Saving your code in a file and running it
Importing code other people have written
Giving each project its own environment
Talking to your computer with the terminal
Saving your work with Git
Putting your work on GitHub
What an array is, and why a list is not enough
Picking out pieces: indexing and slicing, including two dimensions
Maths on a whole array at once, and where you go next
How LLMs Work: Tokens, Context & Sampling
Prompts & the Messages API
Tools, JSON Schemas & Function Calling
Python & APIs for Agents
Git & API-Key Hygiene for Agent Developers
Agent Foundations
Week 1 · 5 lessons
What Are AI Agents?
Agent vs Chatbot
The Observe-Think-Act Loop
Agent Design Patterns
Agent Evaluation
Tool Use
Week 2 · 5 lessons
Function Calling Basics
Defining Tool Schemas
Handling Tool Results
Multi-Tool Agents
Tool Error Handling
Agent Loops
Week 3 · 5 lessons
ReAct Pattern
Plan-and-Execute
Iterative Refinement
Self-Correction
Loop Termination
Memory Systems
Week 4 · 5 lessons
Short-Term Memory
Long-Term Memory
Episodic Memory
Semantic Memory with Vectors
Memory Retrieval Strategies
Multi-Agent Systems
Week 5 · 5 lessons
Orchestrator Pattern
Specialist Agents
Agent Communication
Debate & Consensus
Hierarchical Agents
RAG for Agents
Week 6 · 5 lessons
Agent Knowledge Bases
Dynamic Retrieval
Context Window Management
Grounded Responses
Knowledge Updates
Production Agents
Week 7 · 5 lessons
Human-in-the-Loop
Safety Guardrails
Cost Control
Observability
Agent Testing
Advanced Patterns
Week 8 · 5 lessons
Autonomous Workflows
Agent Chains
Self-Improving Agents
Agent Benchmarking
Deploying Agent Systems
MCP & Agent Protocols
Week 9 · 7 lessons
Why MCP: The M×N Integration Problem
MCP Architecture: Hosts, Clients, Servers & the Lifecycle
Tools: Exposing Capabilities to the Model
Resources & Prompts: Context and Templates
Sampling, Roots & Elicitation: Inverting Control
MCP Security: Trust, Tool Poisoning & OAuth 2.1
A2A & the Protocol Landscape: Agent-to-Agent + Observability
Agent Harness Engineering
Week 10 · 7 lessons
The Agent Harness & the Workbench Loop
Scope Contracts & Repo Memory
Verification Gates: Making the Loop Self-Correct
Reviewer Agents & Multi-Session Handoff
Eval-Driven Agent Development
Agent Benchmarks: SWE-bench, GAIA, WebArena, OSWorld
Capstone — Build & Measure a Coding-Agent Harness
Modern Agent Frameworks
Week 11 · 6 lessons
The Framework Landscape & Build-vs-Buy
The Claude Agent SDK
The OpenAI Agents SDK
LangGraph: Stateful Graph Orchestration
CrewAI & AutoGen: Multi-Agent Patterns
Choosing & Migrating Between Frameworks
Computer-Use & Browser Agents
Week 12 · 6 lessons
Agents That See Screens: The Computer-Use Model
Browser Automation Foundations: DOM, Selectors and Waiting
The Observe-Think-Act Loop
Reliability: Verification, Checkpoints and Human Gates
Evaluating GUI Agents
Production Patterns for Web Agents
Multi-Modal Retrieval
Adaptive Chunking & Indexing
Production RAG Pipelines
Agent Frameworks & Infrastructure
5 lessons
LangGraph Deep Dive
CrewAI & Role-Based Agents
AutoGen & Conversational Agents
Custom Framework Design
Framework Selection & Migration
Enterprise Agent Security
5 lessons
Prompt Injection Attack Taxonomy
Input Sanitization & Defense Layers
Data Exfiltration Prevention
Sandboxing & Execution Isolation
Compliance & Audit Trails
Advanced Multi-Agent Orchestration
5 lessons
Swarm Intelligence Patterns
Agent Markets & Auction Mechanisms
Emergent Coordination & Self-Organization
Scaling Multi-Agent Systems
Cross-Organization Agent Federations
Agent Reliability Engineering
5 lessons
Evaluation Frameworks at Scale
A/B Testing Agent Systems
Observability & Distributed Tracing
Incident Response for Agent Failures
Continuous Improvement Pipelines
Capstone & Research Frontiers
5 lessons
World Models & Reasoning Agents
Tool-Making Agents
Agent-Computer Interfaces
Ethics & Societal Impact of Autonomous Agents
Capstone Project Workshop