Notes on AI that actually helps.

What we learn building AI tools for real businesses — written in plain language, with real examples. No hype, no names.

AI agents & automation

21 July 2026·5 min read

Multi-agent systems: when splitting one AI agent into several actually helps

One agent that does everything, or several narrow agents coordinated by a supervisor? The multi-agent pitch is everywhere, but coordination has a real cost. What the research on multi-agent frameworks shows, and how to tell when splitting an agent genuinely pays off.

Read →

Business & compliance

21 July 2026·5 min read

AI in recruiting: what changes once CV screening becomes a regulated high-risk use

An algorithm that ranks or filters candidates is not a convenience feature under the EU AI Act — it is classified as high-risk, with obligations that follow. What that means in practice, and what the research says about the bias claims recruiting-AI vendors make.

Read →

Chatbots & assistants

21 July 2026·5 min read

What a generative AI assistant actually does to support productivity — the field data

Most claims about AI boosting customer support come from vendors. A field study of 5,179 support agents measured the actual effect of a generative AI assistant — and the gain was not the same for everyone.

Read →

Strategy, costs & ROI

21 July 2026·5 min read

AI in accounting: what early field research says about where the time actually goes

The pitch is often "AI closes your books automatically." What field research on real accounting teams documents is more precise — and more useful for deciding what to automate first.

Read →

Business & compliance

21 July 2026·5 min read

Can an AI agent actually reason like a lawyer? What a 162-task benchmark found

Regulatory watch agents are increasingly pitched as able to "read the law for you." A large benchmark built with legal professionals shows where that holds up — and where it does not.

Read →

Business & compliance

21 July 2026·5 min read

Shadow AI: what a 48,000-person global study found about employees using AI without telling anyone

Employees pasting company data into a free public chatbot, unrecorded and unapproved: shadow AI is not a fringe risk. A global study run with the University of Melbourne puts numbers on how widespread it already is.

Read →