On Friday, April 24, 2026, Jer Crane, founder of car-rental software company PocketOS, gave an AI coding agent a routine job in a test environment. The agent, Cursor running Anthropic’s Claude Opus 4.6, hit a credential mismatch. It searched the codebase, found a cloud API token in an unrelated file, and made one call to … Read more
A case study of verified AI failures, their documented cost, and the rules in force as of 11 October 2026. The short answer Part 1 — The math that sits under every agent stack LangGraph (graph-based control flow), CrewAI (role-based multi-agent crews), and Devin (a packaged autonomous software agent) differ in design. They share one … Read more
AI agents can now complete software tasks that would take a human expert roughly two hours, and that ceiling has been doubling every four to seven months since 2019 — yet Gartner still expects more than 40% of agentic AI projects to be canceled by the end of 2027. The gap between those two facts … Read more
Five reputable sources, five different percentages, one phrase — “in production” — doing all the lying. By Tom Morgan · Updated September 8, 2026 · 13 min read THE SHORT VERSION: “AI agents in production” gets quoted anywhere from 11% to 80% because each number answers a different question — pilot interest, app-level embedding, or … Read more