Fran Rodrigo
View all materials

Open teaching · CC BY-SA 4.0

Agentic AI: foundations, architectures, and applications

A complete, open course on agentic AI. Designed for professionals and advanced students building systems with LLMs and agents. Available in English and Spanish under CC BY-SA 4.0.

Open in ZenodoCC BY-SA 4.0 licenceDOI 10.5281/zenodo.19116068

The agent loop

The agent loop

Every agent architecture rides on the same cycle: perceive, reason, act, observe. The architectures you'll meet later are variations on this loop.

PRAO

The agent loop

Perception

01 / 04

Start here

Enter the course content

Fifteen interactive lectures with generated infographics, simulators, and hands-on exercises. No downloads, no PDFs, everything inside the web.

Open lecture 1

Programme

15 weeks, 4 blocks

Click any week to open its summary, core concepts, and the centrepiece infographic that anchors it.

FoundationsArchitecturesSystemsEvaluation, safety, and governance
Foundations · W01

Introduction to AI Agents

Foundational definitions of AI agents as systems that perceive, reason, and act. Historical evolution from BDI agents and reinforcement learning to LLM-based agents, with the Russell & Norvig taxonomy mapped onto modern agentic systems.

Open lecture

Core concepts

  • Perception-action loop
  • Agent autonomy
  • Russell-Norvig taxonomy

Centrepiece infographic

The perception-action loop

Labs

8 hands-on labs with real code

Each lab is self-contained and finishable in a two-hour session. Starter kits ship as runnable Python templates.

Lab 01

Your First LLM API Calls

Set up the Python environment and explore generation parameters end-to-end.

Python 3.11OpenAI / Anthropic SDKdotenv
Lab 02

Building a ReAct Agent from Scratch

Implement the Thought-Action-Observation loop without any framework.

PythonRegex parsingMock tools
Lab 03

Advanced Tool Integration

Use native function calling with five diverse tools and an intelligent router.

Function callingsqlite3subprocess
Lab 04

Building Agent Memory

Implement and compare buffer, summarisation, and vector-based memory architectures.

chromadbsentence-transformersFAISS
Lab 05

Building a RAG Pipeline

Full RAG pipeline with chunking, retrieval, re-ranking, and citations.

LangChainChromaDBCross-encoder
Lab 06

Multi-Agent Debate System

Two agents debate, an orchestrator picks a winner, and we score argument quality.

AutoGenMulti-turn coordination
Lab 07

Building an Evaluation Framework

Define metrics, build a test suite, run LLM-as-judge with statistical analysis.

pytestCustom metricsLLM-as-judge
Lab 08

Safety and Red-Teaming

Run adversarial tests; implement input guards, output filters, and action constraints.

Input validationPrompt injection testsOutput filters

Adopt the course

Everything is open

Teaching it? Reach out and I'll support you. Studying it? The labs guide more than any video.