Stop Babysitting Your AI: Context Gathering & Code Review, Looped! (with Alexey Verkhovsky)

Stop babysitting context gathering and code reviews: Quick Dev folds BMAD's create-story, dev-story, and review-story into one agentic loop, and in this episode key open source contributor Alexey Verkhovsky walks the whole diagram with Brian: intent, spec, implement, adversarial review, triage. How it evolved and where it is going.Watch the video version: https://youtu.be/ufOyrZhRj6UJoin the BMAD Discord: https://discord.gg/gk8jAdXWmjEverything BMAD in one place: https://bmadcode.com/GitHub: https://github.com/bmad-code-org/BMAD-METHOD/Support the show: https://buymeacoffee.com/bmadChapters:0:00 Welcome to BMad Code Live0:40 Meet Alexey Verkhovsky1:39 Why Quick Dev exists9:06 Quick Dev vs. vibe coding14:36 Context windows and human attention21:18 Brownfield code and the dev-loop question29:53 How big should an intent be?36:46 Walking through the Quick Dev diagram41:26 One-shot mode for small changes45:13 Plan: the story spec template51:00 Implement, then never trust the diff56:54 The adversarial review layers and their cost1:00:00 The valley of despair: triaging AI findings1:03:46 You are the bottleneck, not the AI1:05:59 Customizing the review layers1:11:39 Q&A: do you even need a PRD?1:17:30 Q&A: one model codes, another reviews1:21:28 Quick Dev vs. BMAD Loop vs. Dev Auto1:23:34 Testing, TDD, and the benchmark hype1:31:52 Triage, loopbacks, and fixing findings1:41:05 Deferred work: parking the side quests1:50:49 Present: a narrative for reviewing the change1:56:00 Story, epic, or whole app: how much to batch1:59:48 The story-one tracer bullet strategy2:04:06 Q&A: running reviewers without sub-agents2:06:42 Predictions and sign-off