In depth
An AI agent is the smallest interesting unit beyond a chat completion. It wraps an LLM with three things the LLM does not have on its own: a goal it's trying to accomplish, a set of tools it can invoke, and a loop that runs the model repeatedly, feeding tool results back into context until the model decides it's done. Strip the loop and you have an LLM. Strip the tools and you have a chatbot. Strip the goal and you have a search bar.
What it looks like in practice
YAML
1agents:2 - id: main3 brain:4 provider: anthropic5 model: claude-sonnet-4-66 modules: [filesystem, web]7 system_prompt: "Find every TODO in src/, write a summary."Related concepts
Agent loopThe core runtime cycle of an agent: think, act, observe, repeat, until the goal is reached.Tool useThe LLM capability to emit a structured call to an external function, which the runtime executes and feeds back as context.System promptThe instruction text the LLM sees before any user message. Sets the agent's role, constraints, and behaviour.Multi-agent systemA set of agents that collaborate, typically a coordinator that spawns specialist workers in parallel.
Read the deep dive
What is an AI agent? A 2026 guide for engineers
Read article
Newsletter
Get the next post in your inbox.
Engineering notes from the Digitorn team. No marketing, no launch announcements, no "10 prompts that will change your life". Just the things we write that we'd want to read.