With Claude Enterprise, administrators can configure Claude Code to block commands, restrict file access and control MCP connections across the organisation through centrally manag...
Continue reading
An AI workflow often starts with a set of instructions for one task. You explain how to review a pull request or investigate an issue, try it out, and refine the instructions as yo...
Continue reading
With all the AI skills developers use and create today, and the workflows they build around them, there is a lot of knowledge worth sharing. But taking the step from a personal set...
Continue reading
A queue is growing, exports are waiting, and the service appears to be running. There are several places to look: queue counts, consumers, connections, routing and application logs...
Continue reading
Updated September 15, 2026 with current pricing and provider reporting. For many teams, working with AI agents is already the default way to develop software. Most of the engineeri...
Continue reading
A requirements document gives us something to build against. There is still a planning step between that document and picking up the first issue: deciding how to divide the work, w...
Continue reading
I do not expect many people to use a dedicated MCP server for this blog. But it was a fun project, and it makes a small example you can follow if you want to expose your own conten...
Continue reading
A planning conversation can leave us with a much clearer idea of what to build. But the decisions are still spread across questions, answers and corrections. Before breaking the wo...
Continue reading
An idea can sound clear until someone asks what should happen when it fails, who should be allowed to use it, or what we actually need in the first version. Those questions can cha...
Continue reading
A useful development workflow often contains more company knowledge than it first appears to. The tracker team, engineering conventions and the place to look for logs can all end u...
Continue reading
Sometimes the next step in an investigation is to look at the database. Has a record changed status? Are there other records in the same state? How many were created during the per...
Continue reading
Logs contain a lot of useful information, but connecting it takes work. Whether investigating an alert, checking unexpected behavior during development or following up on a reporte...
Continue reading
Asking an AI assistant to implement a task leaves quite a few things implied. Which requirements should it follow? How should it break up the change? What needs testing, and what s...
Continue reading
A pull request has come back with review comments. Some point to bugs, some suggest a different approach, and others need a conversation before anything should change. Working thro...
Continue reading
AI can be useful in code reviews, but it is easy to end up at either extreme: dismissing it entirely or accepting its findings without checking them. I think there is a practical m...
Continue reading
Writing tickets is probably not the most exciting part of being a developer. You already know what needs to change, but you still need to open the tracker, write the description, a...
Continue reading