Skip to content

AI Agents & Autonomy

Systems that plan and take actions toward goals — using tools, memory, and (often) other agents.

An AI agent is a program that doesn't just answer a question — it works toward a goal by taking a series of actions on its own.

Think about planning a birthday party. You don't finish it in one move: you decide what's needed, check the calendar, text friends, order a cake, then adjust when the bakery turns out to be closed. At each step you look at what just happened and choose what to do next.

An agent works the same way. It plans the steps, uses tools — like searching the web, running code, or sending an email — to actually change things, and keeps a memory of what it has already tried so it doesn't go in circles. After each action it checks the result and decides the next move. Sometimes several agents team up, each handling one part of the job, like friends splitting the party chores between them.

The main ideas

  • Agent architectures — Perceive–reason–act loops, ReAct, and planner/executor designs.
  • Tool use & function calling — Letting models call APIs, run code, search, and act in the world.
  • Planning & reasoning — Decomposing goals into steps; reflection and self-correction.
  • Memory — Short- and long-term memory, and retrieval to persist context across steps.
  • Multi-agent systems — Orchestrating specialised agents that collaborate or debate.
  • Orchestration & safety — Guardrails, sandboxing, and human-in-the-loop for autonomous systems.

NLP & Large Language Models · Reinforcement Learning · Building with AI · AI Safety, Alignment & Ethics

Want to make things?

Head to AI School — AI camps where kids build their own games.