Hub / AI engineering
Checklists, templates and insights for teams building AI into real processes: when to use a workflow or an agent, how to specify a system, how to test it, and what it takes to go live.
The model
Copilot, assistant, agent, agentic system, and who decides at each level.
Retrieval
How an AI answers from your own documents, and which approach fits which question.
Engineering guide
How a system knows when it is unsure, and passes the case to a person.
Testing
How to measure an agent on real cases before it meets your customers.
Free templates drawn from ENGINEER, each with an editable download. Together they take a system from brief to production.
Checklist
Five questions that pick the pattern, and the signs a workflow is no longer enough.
Word template
Eight parts that turn a business brief into something an engineer can build and test.
Spreadsheet
Twenty real failures written as test cases, with a threshold the owner sets.
Word template
What has to exist, and who signs it, before a pilot meets real customers.
Everything on this hub is drawn from ENGINEER, the second book in our series. It covers what an AI system actually is, how to specify, build and test one, and how to take it from pilot to production.
Publishing 7 December 2026.
Running an AI agent on our own agency's helpdesk before offering it to anyone else taught us things a client project would not have. The decisions we would repeat, and the ones we would make earlier.
Agentic coding tools change how software is built, but only when the project instructions, standards, review gates and budgets are right. The setup we use ourselves, and recommend to clients.
"Human in the loop" is a slogan until someone decides where the loop closes. The real design question is the threshold: how sure must the system be before it acts alone, and who decides that, on what evidence.
An agent that cannot be measured is not ready for production. What an evaluation set is, how to build one with your own experts in a few hours, what to measure, and why it has to run on every change.
The engineering story behind our own helpdesk agent: why a generic chatbot could not do the job, how code and documentation are indexed so retrieval is grounded in the actual build, and the decisions that made it safe to put in front of customers.
Retrieval-augmented generation answers from passages that look like the question. GraphRAG adds the relationships between things. Which one a knowledge assistant needs depends on the questions people actually ask.
We design, build and test AI agents and workflows with you, and support them in production.