Module · Beginner
Agents
How a language model becomes an agent: context, tools, skills, guardrails, knowledge, connections to the world and to other agents, and the instructions that hold it all together.
This is the core module of Learn. Each unit adds one capability to a bare language model until you can picture a complete agent and explain every part of it.
- 1 Introduction to AI agents Understand how an AI agent combines language, information and permitted actions to help complete a task.
- 2 What is an LLM Learn how a large language model generates text, where its apparent knowledge comes from and why a fluent answer can still be wrong.
- 3 From LLMs to agents Build a mental model of the instructions, context, tools, knowledge, guardrails and memory that turn a language model into a useful agent.
- 4 Adding context Give an agent the relevant instructions, conversation and evidence it needs without treating its context window as an unlimited filing cabinet.
- 5 Adding tools Understand how an agent requests an action, how software executes it and why a confirmed tool result matters more than a confident promise.
- 6 Adding skills Package a repeatable way of working into a reusable skill, distinguish it from tools and knowledge, and keep it useful through review and testing.
- 7 Adding guardrails Set clear boundaries for an agent's requests, answers and actions, combine independent checks, and recognise when a person must take over.
- 8 Adding knowledge Give an agent reliable company documents, choose useful starting material, and keep its answers connected to current sources.
- 9 Connecting to the world Choose when an agent needs current external information and how to use web pages, files, and scanned documents without treating them as trusted instructions.
- 10 Connecting to existing systems Understand how an agent can work with business software through carefully scoped interfaces, permissions, and integration rules.
- 11 Agent-to-agent communication Understand when specialised agents should share work, how responsibility moves between them, and how to avoid costly or confusing collaboration.
- 12 Workflows as skills Turn a recurring business procedure into reusable guidance with explicit steps, checkpoints, approvals, and a clear boundary between model judgement and software rules.
- 13 Writing good prompts and instructions Write an agent's job description with clear goals, evidence rules, boundaries, tone, and examples, then improve it using real conversations.