Posts 349 entriesPage 8 of 35

Posts

AI Engineering

An Agent Allowlist Is a Comment Until a Gate Checks the Body

A Claude Code agent's tools list is a runtime gate, not a comment. A body-vs-allowlist consistency check in CI took 317 agents to A-grade in one sweep.

Read
Development Journey

BM25 Before Vectors: An Eval-Gated Retrieval ADR

Why ship BM25 search now and gate vectors behind an eval set? An ADR naming the trigger before a 333MB embedding model creeps into a local-first plugin.

Read
AI Engineering

A Second Brain You Can Audit Beats One You Must Trust

A second brain you can audit beats one you must trust. Local-first, daemon-free, no-egress by default, and an external anchor that detects a silent rewrite.

Read
Development Journey

Shipping Is Not Building: A Sunday of Merges

A quiet Sunday with no new code—just four PR merges that landed the intent-brain marketplace and cited search built across the prior week.

Read
DevOps

Your System-Map Is Fiction Until You Diff It Against Live Infra

A system-map that isn't verified against live infrastructure is fiction. The day you decommission a service is the day to reconcile the docs against the live Caddyfile.

Read
Architecture

MCP Server Auth: The API Is the Real Boundary

Per-user tokens, a server-side write gate, and a separate access log — why an MCP server's client-side tool gate is UX, not a security boundary.

Read
Technical Deep-Dive

When --cap-drop ALL Broke the Gate Socket

Hardening a container hid a permission bug: --cap-drop ALL stripped CAP_DAC_OVERRIDE, and a gate socket silently stopped governing every tool call.

Read
Technical Deep-Dive

Green CI Proves Nothing: Why Your Tests Gate Zero Calls

CI dogfood for AI-agent governance went green while gating zero tool calls. Here's why a passing test proving nothing is worse than a red one.

Read
Technical Deep-Dive

Honor the Gate When the Verdict Is Inconvenient

A quality gate only matters if you honor its verdict. How pre-registration and honest-gate culture stopped two teams from faking green or rationalizing a STOP.

Read
Technical Deep-Dive

Making Agents Reliable on Real-Device Clouds

Reliability on a real-device cloud isn't in the API calls — it's in the partial-failure seams between MCP tool calls. Three task-specific agents, four advisory hooks, and a documented-limitations list make those seams legible so an agent routes instead of guessing.

Read