A dark factory for Band Desktop, built on one measured observation: a single strong agent builds faster than a team that splits the code, but it cannot check its own work. So my factory never splits the code. One seat (the printer, Sonnet) builds the whole product. Three seats exist only where independence adds information: a blind examiner (Opus) writes tests from the spec before any code exists and is locked out of the product repository by the macOS sandbox, a forger (Sonnet) attacks every build and prints counterfeit builds to test the examiner, and a clerk (Opus) keeps the requirement ledger and rules on disputes. One dispatch message built all four pocketful stages in about five hours for $52.82 at list price. The examiner's blind suite grew to 1,182 tests and caught all 20 counterfeits served as unlabeled addresses. Official suites, never shown to any seat: 147/147, 33/35, 6/6, 5/5. I also ran the honest baseline: one Opus agent, same spec, no Band. It scored 188/188 on stages 1 to 3 in 26 minutes for $7.18, two checks ahead of the desk. It also shipped four spec violations our forger found and we reproduced by hand: a 500 on a garbage path, a 500 on a deeply nested unknown field, a wrong handle for an emoji email, a 500 on a valid huge hold lifetime. The desk ships none of them. FACTORY.md documents the seats, the sandbox and serve daemon that enforce blindness, mutation testing of the tester, every defect and who caught it, the solo comparison, and an open limits section.
Category tags: