Crosby's founding engineer explains how to build evals for non-verifiable legal reasoning
graceisford · x · 2026-10-08
Crosby shares its founding engineer's post on how they build evals: ten great lawyers will redline the same contract ten different ways — so how do you tell an agent what good looks like? Legal reasoning is the most complex non-verifiable domain, and Crosby opens up their approach to building evals for it.
Full details in the linked post (see the companion item).
Related event: Legal AI Firm Crosby Explains Building Evals for Legal Reasoning(2 posts)→
More from coding & agent
- Obsidian Starter Kit v5 automates archiving, todos and AI context so you stop doing them by hand — dSebastien · 2026-10-08
- DAIR.AI curates 31 papers on recursive self-improvement, from Gödel Machines to today — omarsar0 · 2026-10-08
- "The worst code I've seen was human written": devs push back on AI code panic — DoctorJosh · 2026-10-08
- Short video on the skills modern developers should focus on, flagged as practical — rseroter · 2026-10-08
- The 2026 AI Engineer Checklist: From Python Basics to Shipping a Real Agent — nevrekaraishwa2 · 2026-10-08
- Personal Bridge: an MCP Plugin That Lets Your Dot Read iCloud Mail, Calendar and iMessage — simpsoka · 2026-10-08