#ai

Articles tagged with #ai

Your AI Agent's Mistakes Are a Free Preference Dataset. Stop Deleting Them.
You correct your AI coding agent dozens of times a day. "No, not that file." "Don't force-push to main." "That function doesn't exist — you hallucinated it." Each of those corrections is a perfectly l
Jun 12, 20263 min read
Your team is teaching the same AI agent the same lesson, five times
53% of enterprises now run at least one coding agent in production. 71% of professional developers use one daily. 18% of merged PRs list an agent as primary author or pair-coder. Coding agents are eff
Jun 7, 20263 min read
A dashboard isn't agent governance: the case for pre-action gates
A study from the Cloud Security Alliance and Token Security, published in April 2026, found that 65% of organizations had at least one security incident caused by an AI agent in the past year. 61% of
Jun 5, 20265 min read
Your compliance team will ask for an AI agent audit trail before August 2. Here's the part most teams haven't built.
title: "Your compliance team will ask for an AI agent audit trail before August 2. Here's the part most teams haven't built." published: false description: "The EU AI Act's high-risk obligations reach
Jun 4, 20268 min read
You automated away the human approval step in CI/CD. You didn't replace what it was doing.
Agents now open PRs, approve low-risk deploys, and run overnight loops with no one watching. Sandboxing bounds what they can reach; RBAC bounds their credentials. Neither bounds what they're allowed to do within reach at 3am. Here's the deterministic control-plane bound that does — and how it composes with the isolation you already run.
Jun 1, 20264 min read
Prompt injection is structurally unfixable at the model layer. Move the defense to the tool-call boundary.
The numbers we have to start with Three datapoints from the last 90 days, all dated and all public. GitGuardian, March 17, 2026. The State of Secrets Sprawl 2026 report found 28.65 million new hardcod
May 29, 202615 min read