I built a macOS app on a 9½ hour flight after work because I was tired of files named "Screenshot...
I built a macOS app on a 9 hour flight which renames your Downloads folder full of junk
I built a macOS app on a 9½ hour flight after work because I was tired of files named "Screenshot...
What Adobe's Workfront MCP server does, where it stops, and what a verified Claude toolkit does differently — findings from production, with timings.
A forged confirmation, falsely green tests, and the acceptance gate I built afterward.
Same model, different harness: why agent reliability depends on the system around the model.