Journal

Here I write about how I work with coding agents and the questions that come up along the way.

Updated 9 Nov 2026

Introducing Claude Code to a development team: rules, review, costs

What I would settle before a team uses coding agents day to day, and what I know about it from my own setup.

Updated 9 Nov 2026

Running MCP servers safely: permissions, secrets, prompt injection

How I limit my own and third-party MCP servers in my agent setup, and where those limits end.

Updated 9 Nov 2026

Keeping the token costs of coding agents under control

How I combine subscriptions, daily budgets and routing so agents do not get expensive without anyone noticing.

Updated 1 May 2026

What I learn from operating AI agents

Why I treat routing, handoffs and reviews as parts of the same system.

Updated 29 Apr 2026

How I write tasks for agents

A task needs context and a result that can be checked.

Updated 25 Apr 2026

What I put in agent instructions

Project-specific rules need a source and a clear scope.

Updated 19 Apr 2026

What context I give agents

Relevant sources, open questions and handoffs between sessions.

Updated 15 Apr 2026

How my agent platform, Harness, routes tasks

Routing by cost, remaining quota and failure history.

Updated 20 Mar 2026

The boundaries I set for AI agents

Limit access and enforce rules in the system.

Updated 20 Mar 2026

How I assess AI tools

A concrete task is a better starting point than a feature list.