Claude Code runs A/B tests on your workflow, and one variable turns them off
Claude Code runs A/B tests from a remote flag service that release notes never mention. How to see yours, switch them off, and why vendors should say so.
Read the post
I'm Chad Norman. I've spent 15-plus years in IT, at startups, SMBs and enterprises, working across infosec, cyber, cloud architecture and, lately, GenAI. Along the way I collected 30-odd IT certifications; like diamonds, they're not all equally cut. This is where I write down what I've learnt, and what I think about it.
InfoSec · CloudSec · Threat hunter
From threat hunting to cloud security, with a habit of tinkering with GenAI and automation. The opinions here are my own.
Writing here, building with GenAI and agents, and working out how to secure them.
Latest writing
The newest posts, in date order.
Claude Code runs A/B tests from a remote flag service that release notes never mention. How to see yours, switch them off, and why vendors should say so.
Read the post
Short-lived credentials limit how long an AI agent holds access, not what it can do. Put hard limits in code first, then shorten the tokens.
Read the post
This blog runs on Cloudflare's free plan for R0 a month. What a developer starting out gets there, what they still own, and where the deal stops.
Read the post
A sample post that shows how posts render on this site. It will be replaced.
Read the post
Autonomy is a permission you grant a model, not a feature it has. Five levels for AI workflows, and how to pick the lowest one each step can live with.
Read the post
Topics
Notes
Short ones: things I learnt, links worth reading, quick takes.
Simon Willison's lethal trifecta applies to the agent on your laptop. Three questions to ask before you add the next MCP server.
Follow along
Every post and note, in full, in the feed reader you already use. No email address and no tracking pixel.