ai
6 posts tagged "ai"
What Your Agent Logs Can Actually Prove
I tried to check which documents a coding agent had received. The records and text matches could support a much more reassuring account of the work than the evidence justified.
The Agent Harness Belongs in Your Release Process
A coding agent can pick up a changed document halfway through a task. That behavior needs to be part of how we test and approve it for engineering work.
The Next Golden Path Is for Agents
Platforms have always served two kinds of users. The organization standardizes most teams onto a managed path and trusts a few to work directly with the primitives. Agents are a third user that fits neither path, and the next golden path has to be designed for them.
AI Needs the Context Auth Was Built to Limit
Access controls were built for two cases: automated workloads with a predictable footprint, or a human stitching tools together by hand. AI agents are neither, and the Vercel incident previews what breaks when we stretch the old model to cover them.
AI Is Forcing the Platform Rebuild That Should Have Happened Years Ago
AI adoption at scale keeps failing for the same reason platform engineering never got funded. Now they are the same investment.
Ungoverned Context Is a Real Supply Chain Risk for Agentic Workflows
Ungoverned context is a real supply chain risk for agentic workflows. Most teams can identify the agent's runtime but have no way to reconstruct what sources actually shaped the output.
← All posts