A hands-on workshop for one engineering team
The Agent Workshop
Building agents that work more than once. Delivered remotely or on-site, on a prepared repository or your own systems where the team wants to go further.
The premise
Where agents break.
A tool returns something the model can't interpret. The context fills up and the agent loses the thread. Nothing in the system can tell a good run from a bad one.
All three are engineering problems with known solutions, and the session fixes them in code.
What you build
Four things, on a real codebase.
The harness
What the agent can see, what it may do, what happens when a tool fails, and how the loop knows to stop.
Tool contracts
Tool descriptions as interface design, useful error messages, return values shaped so the model doesn't have to guess.
Context strategy
Where context goes, why long-running agents degrade, and the practical answers: compaction, handoff, scratch files, sub-agents.
Evaluation
A small evaluation over your own agent, broken deliberately, so you can watch it catch the failure.
Prerequisites
JavaScript, TypeScript or Python. At least one prior LLM API call. A machine you can install packages on and a key for any major provider.
No machine learning background, no particular framework, and the exercises cost a few cents of model usage to run.
AI Engineering for Web Developers
Covers this ground in writing, in the same voice, with no sign-up. The way to judge the teaching before booking anything.
Read the book For the rest of the organisationThe Power User Gap
Where the wider problem is that most of an organisation never got past asking these tools questions, that's a different session.
About the session
Who you'd be working with
I build agents and harnesses every day and write about it in the open. The free book is the same teaching in written form.
Google Developer Expert in Web Technologies, Agentic AI Foundation ambassador, MBA. 25 years across software engineering, developer relations and technical training, and 138 talks and workshops in 33 countries.
More about meBring it to your team.
A paid engagement, quoted against scope. Email with what the team is building and where they're stuck.