Method notes.
What we learn from surveying systems and opening them: the rule, the case, the limit. One note per subject, written once the subject has been measured — never because the calendar says so.
AI agent or plain automation: the £20,000 question
A third of the use cases brought to us need no model at all. How to tell a workflow from an agent, and why getting it wrong is expensive in both directions.
4 September 2026 · 6 min read SystemsYour document base, or why the agent answers beside the point
An agent is only worth what it can read. The four defects that produce answers beside the point — duplicates, undated versions, scanned PDFs, implicit context — and the preparation that fixes them.
2 September 2026 · 6 min read Responsible AI« What if it makes things up? » — getting an agent to cite its sources
A model produces a plausible sentence, not a true one. The four designs that make invention visible, and the single rule that matters: every claim points to its source.
14 August 2026 · 6 min read SystemsGetting cited by ChatGPT and Perplexity: what actually works
Generative engines cite what they can read, structure and verify. Five concrete moves — including serving your pages as Markdown — and what is a waste of time.
10 July 2026 · 6 min readWe will tell you which system to open first.
Describe the task that costs you the most. We will tell you what is feasible, how long it takes and what it costs. If the answer is no, you will leave with the two reasons why.