PHINEAS
A staged LLM pipeline for CEFR-aligned vocabulary instruction. A word's level is data, served from a part-of-speech-aware database, so the model handles only the unknown words and the human-facing prose.
Read more
Forward Deployed / Applied AI & AI/ML Technical Program Manager
Closing the gap between AI demos and AI production, between proofs of concept and operations at scale.
10+ years of complex program delivery at Google and Meta. $50M+ in capital programs across Google, Meta, FORTÉ, and NTT. 100+ station Starline fleet. Production AI systems built and deployed in real environments.
A staged LLM pipeline for CEFR-aligned vocabulary instruction. A word's level is data, served from a part-of-speech-aware database, so the model handles only the unknown words and the human-facing prose.
Read more
The public TypeScript flagship of the Limner family: a harnessed image agent where Claude reasons and Cloudflare executes the tools in a V8 isolate, with D1 for memory. The agent gates its own output against a stylistic bar and rejects work that fails.
Read more
A portable, versioned Skill Card standard for Claude Agent Skills. It pairs an NVIDIA SkillSpector security scan with a trigger and task-completion eval harness, keyed to a content hash so a card always describes the exact skill it was built from.
Read more
· 5 min read
An HR consultant asked for pixel art. The discipline that came out of it turned into something I now call agent husbandry.
· 7 min read
Independent LLM evaluators disagree, and averaging their scores hides the disagreement instead of resolving it. Here is a three-round method that surfaces the conflict, reconciles it through structured debate, and converges on an auditable result.