Writing
Notes from building two systems: an assistant that answers from the EU AI Act and cites every sentence, and an agent that writes to Asana and HubSpot only after a person approves. Each article says what I measured and what you can reuse without hiring anyone.
New articles also arrive by RSS.
Case study: AI service delivery coordinator
Human approval for AI agents that write to real tools
How to let an AI agent change Asana and HubSpot safely: the model drafts, code does the dates, a person approves one exact version, each write happens once.
Case study: EU AI Act compliance assistant
How to stop a RAG assistant inventing citations
A RAG assistant that cites sources can still invent them. How I verify every citation and every sentence in code, refuse when a check fails, and log why.
Case study: EU AI Act compliance assistant
When hybrid search scores worse than vector search
Adding BM25 to vector search cut my RAG assistant's recall@5 from 0.86 to 0.58 on 36 labelled questions. What I tried, what I shipped, and what to test first.
Tell me what is eating your team’s week.
Send a short brief: what the work is, who does it now, and what it costs you. I reply within two working days with a rough scope, a price range and whether AI is the right tool for it at all.
Send a briefOr write to [email protected].
- Defects fixed at no charge for 30 days after a build’s handover
- Stop partway: pay for the work done, keep the code
- No mark-up on model usage