Launch HN: Momentic (YC W24) launches Mo, a QA agent that finds bugs at $2.67 each
wuweiweiwu · hn · 2026-11-03
Momentic (YC W24) launched Mo on Hacker News: an autonomous QA agent that plans, explores, and bug-bashes web, iOS, Android, and soon desktop apps.
- Founders from Robinhood/Retool/Qualtrics argue hardcoded E2E frameworks (Playwright, Selenium) are fundamentally misaligned with the agentic SDLC; the future is agents testing agents, not scripts.
- Key datapoint: on DeepSWE v1.1, Sonnet scored 66.2% pass rate when banned from writing tests vs 65.3% when allowed — LLM-written tests reinforce their own assumptions.
- Mo, trained on millions of real-world test traces, optimizes for recall: 84% precision vs Codex's 86%, at $2.67 per bug vs $0.80 for Codex — still cheaper than Claude Code and Devin.
More from coding & agent
- Dev builds fully personalized UIs for agents, email and Slack with Claude — zack_overflow · 2026-11-03
- Superserve (YC F26) launches agent cloud, already spinning up 100K+ machines weekly for YC and Lindy — ycombinator · 2026-11-03
- Lantern (YC) launches People Infrastructure for Agents, aggregating 70+ tools behind one CLI connection — ycombinator · 2026-11-03
- Rumored Claude Fable 5.5 beats Opus 5.5 and Gemini 4 Argon on three.js giraffe test — minchoi · 2026-11-03
- Dan Shipper: Partly Argon impresses while Antigravity feels stuck in 2025 — danshipper · 2026-11-03
- 'Opus 5.5 refactored my codebase into a Grosse Fuge — my team hates it, history won't' — eigenron · 2026-11-03