Ways to build an AI agent
Some work is better handed to an agent than done one prompt at a time. An agent is AI that pursues a goal by taking steps on its own, choosing and running tools, reading the result, and deciding what to do next, all within the bounds you set. This page is about designing that well: what the agent can reach, how it decides, and where it has to stop and hand back to a person.
Say it another way
What is an agent, in plain words? Usually you tell the AI one thing and it does that one thing. An agent is AI you hand a goal to instead, and it works out the steps itself, does them, checks how they went, and decides what to do next, until the goal is met. It is the difference between talking someone through a recipe step by step and simply asking them to make dinner. The real skill is deciding what it may do on its own, and where it has to stop and check with you.
What this will cover
The moves for designing and building agents: giving them well-described tools and only the ones they need; deciding what runs autonomously versus what pauses for a human; and handling errors so a single failure does not derail the whole run. I build this for real in the flowRun project, so the worked version grows alongside it.
This page is lighter than the others for now, with more sections still to come.
In plain words
In plain words: this page is about building an AI agent, which is AI you hand a goal to so it works out and takes the steps itself, choosing and running tools, within limits you set. It will cover how to give an agent the right tools and only those, how to decide what it does on its own versus what it checks with you, and how to handle errors so one failure does not derail the whole run. This page is still growing.
Part of Working with AI. The soft skills behind it: The soft skills of working with AI.
Why Claude. When this page carries tool-specific notes they use Claude Code, because it is one of the most widely used AI tools for building software. It is also what we build with day to day. The moves themselves are general and carry across to other capable AI tools.