KZkevinz.ai
--:--:-- -- EST · YYZ
← all topics
→
Field Report·May 08, 2026·6 min
Anatomy of an 87% Dispatch Failure: How One Missing Schema Field Killed Our Agent Fleet
49% of our agent dispatches were failing for three weeks. The bug was one stale field in the adapter.
→
Field Report·May 01, 2026·12
10 Real Agent Failures + How I Diagnosed Them
Ten real OpenClaw fleet failures from my 57-agent stack, the signals that exposed each one, and the preventive fixes I shipped.
→
Field Report·May 01, 2026·8
4 Shell-Injection Vectors I Caught In My Own Agents
A security field report on four prompt-to-shell injection paths I found while hardening my OpenClaw agent fleet.
→
Field Report·May 01, 2026·10 min
Config Drift Killed My Deployment — Here's the Guard I Built
openclaw.json is 139KB of routing + agent config + model aliases. Unauthorized changes break things silently. Here's the SHA256 guard I built after one Tuesday morning broke everything.
→
Field Report·May 01, 2026·9
How I Track 57 Agents' Cost Without Burning Agent Cost
A field report on the local-first cost loop I use to track 36 OpenClaw agents, catch spend spikes, and keep the watcher off the bill.
→
Field Report·Apr 17, 2026·8 min
Letting Claude Code Run Unsupervised for 8 Hours: A Field Guide
What actually happens when you leave Claude Code running overnight — the setup, the checkpoints, the failure modes I've hit, and the security constraints that keep it from going sideways.
→
Field Report·Apr 14, 2026·9 min
I Let AI Manage My Smart Home for 2 Weeks
1,119 entities. 30% offline at start. AI fixed them while I slept. The unglamorous truth about agents in the physical world.
→
Field Report·Apr 10, 2026·5 min
Why WhatsApp Is the Future of Retail Authentication
Email forms are leaking. Facebook OAuth deprecated overnight. WhatsApp login is filling the gap — and the open rate numbers make the case obvious.