Building Typewright, an alpha compiler for typed AI decisions, with research-cited design, hashed evidence, and an honest negligible live gain.
JEV Sentinel returns typed verdicts for agent prompts, tool calls and results: deterministic rules first, model judgment can only add vetoes.
An offline evaluator that finds judgment calls in code, gates every change behind approval, and runs studies allowed to say no. Five of six did.
Four agent skills that draft emails, contracts and invoices from shared state, with approval gates, TBD markers, and a run on fictional data.
A read-only Python tool that inventories on-premises ServiceDesk Plus across portals and reports Cloud migration gaps instead of guessing.
Building England Crime Atlas: Police.uk crime on a 2 km grid, a separate court-outcome view, snap-point anonymisation, and why counts are not rates.
How LibreEvolve structures code-evolution experiments, what its reproducibility records cover, and an offline bin-packing run with a mock model.
Structuring AI agent judgments as typed decisions with strict validation, policy in code, and hash-chained receipts you can replay.
Rating NYC 311 complaint text against a fixed rubric, validating every model answer, and mapping results on a 500 m grid. Volume is not incidence.