Dev running multi-human, multi-agent codebase: all serious architecture must pass human review
bradneuberg · x · 2026-10-15
Developer seanfromearth shared rare hands-on experience running a codebase with multiple humans each using AI agents: every serious architecture decision goes through him or his best staff engineer, no exceptions.
He admits he works harder than pre-AI, but relaxing the rule always lets slop sneak in. He blames himself for not building the right training and systems. bradneuberg adds that writing RFCs before major work helps—giving AIs an initial plan and constraints for future AI work to fit into.
More from coding & agent
- One-page cheat sheet maps Kiro, Claude Code, Codex and Cursor feature names — DigitalColmer · 2026-10-15
- One-man software factory: 5-10 parallel agents build POCs, 60% get killed — Stefania_druga · 2026-10-15
- Huawei's SwarmRSI: evolving agent swarms achieve recursive self-improvement in science — Qianru Meng · 2026-10-15
- Prompt With Love: Steering Massive Agent Swarms With Values, Culture and Story — liminal_bardo · 2026-10-15
- Vibe First, Validate Fast: One Chart Nails How AI Development Differs From Agile — burny_tech · 2026-10-15
- A Year of Agent Memory Evolution: From Static CLAUDE.md to "Dreaming" — mcraddock · 2026-10-15