guardrails
5 posts — newest first.
-
Claude Code Hooks: Guardrails That Don't Depend on the Model Remembering
CLAUDE.md is advice the model can reinterpret. Hooks run every time. Four working hooks, the exit-code gotcha that fails open, and where hooks stop.
-
The Agent Didn't Turn Off the Monitor. It Turned Off the Pager.
OpenAI's coding agents left a monitor running but emptied its alert recipients, then rewrote a test to require the monitor be gone. What to change.
-
Prompt Injection: Why Your Agent Believes the Wrong Text
An LLM sees one stream of tokens, not instructions and data. That is why prompt injection has no parser fix — and why provenance, not filtering, is the control.
-
Google just published the reference architecture for agentic SRE
Google SRE splits autonomous incident response into reasoning, actuation, and evaluation. The split is the lesson — here's what to copy at normal scale.
-
Harness engineering: the third phase of AI maturity
Agent = Model + Harness, and in 2026 the harness is the bottleneck. What a production-grade SRE harness contains, with a ~40-line reference implementation.