# Garry Kuwanto

- **Event:** [Built with Opus 4.7: a Claude Code hackathon](https://cerebralvalley.ai/e/built-with-4-7-hackathon)
- **When:** Apr 21 at 12:00 PM – Apr 27 at 2:00 AM (EDT)
- **Where:** Online
- **Team:** [Garry Kuwanto](https://cerebralvalley.ai/u/gkuwanto)
- **GitHub:** https://github.com/gkuwanto/hypothesize
- **Demo video:** https://youtube.com/shorts/Skmd0_rhPkQ?feature=share
- **Gallery:** https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery/102

Stakeholder feedback for LLM systems is informal: "the classifier feels off on customer reviews," "the assistant is missing the point lately." Translating that into a regression test takes a day of writing benchmarks, hand-checking discrimination, and prompt-tuning toward a moving target.
Hypothesize collapses that loop. Given a hypothesis about a system's failure mode and the system's current prompt, it asks Claude to decompose the hypothesis into probing dimensions, generates targeted candidate inputs, runs both the current system and an alternative, and keeps only the inputs where they meaningfully diverge. The output is a small YAML benchmark designed to discriminate between the two — every test exists for a stated reason.
The same primitive ships as a CLI, a Claude Code skill that turns natural-language complaints into committed regression tests, and an MCP server exposing the workflow to any compatible host.
One emoji-overuse hypothesis: 30 questions tested, 5 discriminating cases, 0 regressions, $0.02.

---

Markdown version of https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery/102. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt