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.

Strategy, costs & ROI

21 July 2026·5 min read

Fine-tuning or better prompting: which one actually fixes your agent’s weak spot

When an AI agent gets something wrong, the instinct is often "we need to train it on our data." Most of the time, a better-designed prompt and retrieved context fix the problem faster, cheaper, and without the risks fine-tuning introduces.

Read →

Business & compliance

21 July 2026·5 min read

Prompt injection: the security risk that comes with giving an AI agent access to outside content

An agent that reads an email, a web page or a document to complete a task is also reading whatever instructions someone slipped into that content. Prompt injection is the security problem that comes with agent autonomy — and it has no complete fix yet.

Read →

AI agents & automation

21 July 2026·5 min read

Observability for AI agents: why "it worked in the demo" is not a measurement

A chatbot that handled the ten questions in a demo perfectly can still fail silently on the eleventh, in production, with no one noticing. Observability and structured evaluation are what turn "it seems to work" into a number you can track.

Read →

AI agents & automation

21 July 2026·5 min read

AI agents for medical secretarial work: what a randomized trial found about time saved and burnout

An AI agent that drafts a consultation note from the conversation is one of the few agent use cases with a real randomized trial behind it. What it found — and what it did not — sets realistic expectations for the sector.

Read →

Strategy, costs & ROI

21 July 2026·4 min read

The real running cost of an AI agent: it is not the build, it is the tokens

The invoice for building an agent is a one-time number. The cost that determines whether it stays profitable is the one paid per request, forever — and it has been falling fast enough to change what is worth automating.

Read →

Business & compliance

21 July 2026·5 min read

Why an agent should see less data, not more: minimization as a design rule, not a compliance afterthought

The instinct when building an agent is to give it broad access "just in case it needs it." Research on what large models retain from what they process shows why that instinct is exactly backwards.

Read →