What changed this week, and what it means for you.
Analysis of what is new in the field, written for the people who have to decide. A new article every Sunday.
-
Code review when AI agents write most of the code
The Claude Code team at Anthropic has published how it reviews code when an agent writes about 90% of it. What worked for them, what data from other…
-
Not every automation decision needs a large language model
Routing requests, classifying them and answering yes or no make up most of the work in business automation. Small models that return a decision instead of text do…
-
What to check before installing a skill for an AI agent in your organization
Skills and plugins make AI agents more useful, and they also give attackers a way in. What security researchers found in 2026, and what to check before installing…
-
When an AI agent tries to fill in the form on your website
Google added a check to Lighthouse that shows whether AI agents can work with a website, and Cloudflare built a check of its own. What gets tested, what…
-
From an AI-built prototype to a product you can trust
In the first weeks everything moves fast, and then every fix breaks something else. What the data shows about code written quickly with AI, and what needs to…
