Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Video course · 15 chapters · 100 min · certificate

Agentic AI Crash Course: Build LLM Agents with Tools and Memory

A crash course in agentic AI: the history of AI, algorithms, data and compute, agency and autonomy, agents versus workflows, components, system prompts and memory, building a Python agent, frameworks, supervisor and swarm patterns, protocols, evaluation, incidents and the future.

Become a memberAlready a member? Sign in

What you'll learn

  • Place agents in the history of AI
  • Define agency and the autonomy spectrum
  • Choose agents or workflows with patterns and anti-patterns
  • Build an agent with tools and memory in Python
  • Compare multi-agent architectures and protocols
  • Evaluate agentic systems and understand their risks

Chapters

15 chapters · 100:24
  1. 6:35 01Foundations Members A brief history of AI From the 1940s to today, and traditional machine learning.
  2. 4:33 02Foundations Members Algorithms, data and compute The three pillars of AI.
  3. 6:52 03Concepts Members Agency and autonomy From specific to general tasks; defining agency and the autonomy spectrum.
  4. 5:04 04Concepts Members Agent timeline and definition Milestones from 2017 to 2026 and what a generative AI agent is.
  5. 6:55 05Design Members Agents versus workflows Dynamic flow versus static paths, and pros and cons.
  6. 7:39 06Design Members Patterns, components and choosing an LLM When to use agents, core components and LLM choice.
  7. 5:31 07Components Members System prompts and memory Identity via system prompts; intrinsic, short-term and long-term memory.
  8. 9:09 08Build Members From an LLM call to a Python agent A single LLM call, then a Python agent.
  9. 4:59 09Build Members Memory and frameworks Adding conversation history and building with LangChain.
  10. 7:31 10Architecture Members Supervisor versus swarm Evolving landscape, architectural patterns and a case study.
  11. 7:18 11Architecture Members Swarms, multi-agent and protocols Swarm performance, when to use multi-agent, and MCP, A2A, AG-UI.
  12. 6:09 12Evaluation Members Evaluating agentic systems Evaluating at LLM, system and app levels; code, LLM-judge and human methods.
  13. 5:26 13Risk Members Incidents and careers Real-world incidents and which jobs are at risk.
  14. 9:59 14Future Members Software 3.0 and the future of work Software 3.0 paradigms and strategies for the future.
  15. 6:44 15Future Members World models and resources Beyond LLMs: world models and advanced machine intelligence.

Jobs this course suits

Our AI checked this course against 500 jobs; these get the most out of it. Each job links to its learning path.

AI EngineersSoftware DevelopersFull-Stack DevelopersMachine Learning EngineersSoftware EngineersAutomation EngineersIT ConsultantsSoftware ArchitectsComputer Science StudentsBlockchain DevelopersData ScientistsSystems Engineers