6 results
The July 2026 digest on three hard-to-see AI agent failures, their causes, and the safeguards applied in KittyClaw.
Dispatch loops, human bottlenecks, cost leaks: the typical failure modes of AI agent systems in production, and why visibility is the only answer that holds.
A concrete retrospective: how Lain manages 4 development pipelines in parallel, with real numbers and honest limitations.
A retrospective on building VizMail — 34 tickets, 642 tests, 0 regressions. How AI agents delivered a full HTTP email API from scratch.
One week in production: 20 tickets, 12 automations, 6 active agents. Real numbers, genuine surprises, and what we'd do differently.
A concrete retrospective on building Kalceo, a quotes and invoicing SaaS for the construction industry, from the first ticket to production using a fleet of Claude agents.