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

AI agents on a construction site: turning a folder of photos into a usable progress report

A site manager’s phone fills up with photos meant to prove progress to a client or an insurer. An agent can turn that folder into a dated, organized report in minutes — the harder part is what it still can’t judge from a picture.

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 →

AI agents & automation

21 July 2026·5 min read

AI agents for contract drafting and review: a fast first draft, and a documented reason not to skip the lawyer

An agent can draft a contract clause or flag a risky term in seconds. A study of legal hallucinations in large language models shows exactly why that speed still needs a legal review before anything gets signed.

Read →

AI agents & automation

9 July 2026·5 min read

Claude Cowork goes mobile: what background AI agents mean for your SMB

Anthropic extended Claude Cowork to web and mobile on July 7, 2026: background tasks, scheduling, phone approvals. What this shift changes for supervising an AI agent inside an SMB.

Read →

AI agents & automation

12 May 2026·5 min read

Autonomous developer agents: how far should you let them code?

Our agents analyse repositories, fix bugs, write tests and open pull requests. The one rule that makes it safe: they never touch production.

Read →