How Multica uses Multica to build itself: full human-agent dev workflow
jiayuan_jy · x · 2026-11-04
jiayuan shares a detailed workflow chart of "how we use Multica to build Multica," showing a human-agent split across the whole dev loop: agents triage issues and draft RFCs, humans review; agents write code, a second agent reviews, tests run on a Mac mini; humans approve merges and releases. On the release side agents handle deploy, tagging, preflight checks, multilingual logs (Eve), changelog cleanup (Wall-E) and an Autopilot for short-release issues, with user feedback flowing back into the backlog. Humans keep only review, approval and acceptance gates.
More from coding & agent
- Binance details how $6.34B was stolen: wallet engineer infected via fake take-home job assignment — mfckr_eth · 2026-11-04
- Reply to Karpathy goes viral again: devs who refuse AI coding will be replaced first — CtrlAltDwayne · 2026-11-04
- Visiting Databricks APAC HQ: hands-on with CLI to explore enterprise agent use — FuSheng_0306 · 2026-11-04
- DeepSeek Harness hits Bilibili: 1M views in 12h, devs build 6 killer plugins in days — lxfater · 2026-11-04
- Open-source terminal-mac gives AI agents their own Mac running inside your terminal — _AustinCalvert_ · 2026-11-04
- Decision models match Gemini for RAG conflict typing at 1/39 the cost and 6x speed — parvkhatri · 2026-11-04