Notes on building reliable automation
August 24, 2026
Your Test Suite Does Not Need Another Dashboard: Local Test Pulse for Omarchy
Local Test Pulse reads the report your test runner already produced and turns it into a trustworthy Omarchy bar signal. No cloud dashboard, no test execution, no telemetry, and no false green for stale or malformed data.
Read Article →
August 24, 2026
A Security Indicator Must Refuse to Lie: Building Omaudit Status for Omarchy
Omaudit already scans plugin capabilities. Omaudit Status adds a bounded desktop signal, then treats every green or amber state as a claim that must be tied to the exact audit scope that produced it.
Read Article →Updated 5 Sept 2026
Stop Teaching Browser Agents the Same Workflow Twice
When a browser path already worked, rediscovery is waste. Flow2Skill treats a Playwright demonstration as compiler input and exports both a portable agent skill and a regression test that can prove the flow still works.
Read Article →Updated 5 Sept 2026
Memory Is Not a Lock: How OutcomeLock Stops Agents from Repeating Finished Work
An agent can remember that work is complete while an older action remains queued. OutcomeLock adds a deterministic evidence gate between plan and act so stale work is suppressed before it creates another side effect.
Read Article →Updated 5 Sept 2026
The IDE Needs a Flight Recorder, Not Just an AI Chat Panel
Antigravity, Claude Code, Codex, Cursor, and JetBrains AI already prove the agentic IDE is real. The next battle is not autonomy. It is accountability: durable traces, replayable runs, approval boundaries, and proof that the agent actually did what it claimed.
Read Article →July 03, 2026
How to Test AI Agents: A Practical Harness-Based Guide
A practical guide to testing AI agents with harnesses, traces, outcome checks, deterministic graders, and automation-testing discipline instead of vague prompt reviews.
Read Article →