Hi there👋 — I am Caio Theodoro, a Senior AI Engineer.

Currently

Senior AI Engineer at Adopt AI — Full-time, since Mar 2026, California, United States · Remote. Production AI workflow infrastructure: agent execution, human review, evaluation, and orchestration.

Selected work

• ReconForge — Laptop-trained 1.7B LoRA for financial reconciliation exceptions — 0.913 severity-weighted recall against a frontier model's 0.872, 1.000 recall on high-severity cases, zero API cost.
• Suture — 8B VLM that diffs an underwriting binder against the issued policy: 0.959 recall across 13 discrepancy classes where zero-shot GPT-5.6 vision scores 0.373.
• LossBench — Scores money-touching agents on expected operational loss instead of accuracy — severity-weighted, calibrated, replayable, on a hash-chained decision ledger.

Recent writing

• Ornith-1.5 Wrote Its Own Training Data. Distribution Match Won — Ornith-1.5 proposes its own training curriculum. I audited it with contamination-controlled data on a verifiable niche, construction pay-app review, and found the harder tasks it invents only help as a supplement, not a replacement, for distribution-matched data.
• Suture: Catching Underwriting Errors GPT-5.6 Missed — An 8B vision-language adapter trained to diff underwriting binders against issued policies catches far more errors than GPT-5.6 Luna does zero-shot. The real story is the three measurement gates that gave false confidence before the model actually worked.
• The Third Number — Agents that touch money get evaluated on accuracy or price. Neither one catches the failure that actually costs the most: a single bad decision with an outsized loss. This is about the metric that does, and why nothing measured it before LossBench.

For agents and crawlers

Every page here has a markdown twin: request it with Accept: text/markdown, or append .md to any path. /llms.txt says what this site is for and when to use it; /contact is the way to reach a human.