Search
Posts
Let the Model Judge. Make the Code Decide.
A production writing pipeline rebuilt around one rule: the language model owns judgment, deterministic code owns the gates and the audit trail.
ReadCopying Files Is Not Installing
A marketplace install copies a plugin's files into place but never runs its installer. Here is how that bricked local mode and the dependency-free bootstrap that fixed it.
ReadProducer Fallback: When Claude Hits the Weekly Limit, the Pipeline Still Ships
A weekly LLM limit is a producer outage, not a reason to miss the daily post. Grok fallback + land path kept startaitools shipping.
ReadExit 0 Is Not Success: Automation Assurance That Verifies Outcomes
A green exit code can hide a dead job. Intent-OS automation assurance treats outcome verification as the success criterion, not exit 0.
ReadEmpty Is Not Clean: Five Fail-Open Bugs in an AI Agent
One fail-open bug, five disguises: empty args, an empty log, a missing property, a sheared chain, an unset scope. When there's nothing to check, fail closed.
ReadThe Kernel Must Not Import Its Agents
We extracted a stateful watcher agent from a governance kernel and enforced a one-way agent-to-kernel dependency edge — the kernel must not import its agents.
ReadMaking a Fire-and-Forget Writer Safe Under Failure
Five properties an unattended capture hook needs before you turn it on: idempotent intake, durable outbox, backpressure, atomic receipts, consent gate.
ReadLiveness Without Health Is Theater
A heartbeat that fires on every run proves a job ran, never that it succeeded — the fix is two markers plus meta-monitoring the watchers.
ReadAdversarial Review: The Six Lenses That Halted a Rollout
A six-lens adversarial review checked a team knowledge system against live state, broke three shipped assumptions, and gated 18 risks to halt the rollout.
ReadFix the Dependabot Pile-Up: Policy Over Patches
15 dependabot PRs piling up? Stop merging individually. Group minor/patch updates, auto-merge when green, keep security updates isolated.
Read