I built the same MVP twice. The autonomous agent wrote 4.6x more tests — none caught two stubbed core methods.

Side-post in the keppt build-in-public series — an interlude before the Phase 1 implementation write-up lands. While building Phase 1 of keppt , I ran a side experiment. Same architecture spec, two builds. One I curated over a day with Claude Code and Codex — plan first, tasks derived, agent-implemented per task, adversarial review, iterate. One I handed off to Factory.ai's Droid in their new Mission Control mode. Spec in, walk away, come back when the budget runs out. Here is what came back. th