Omar Espejel
Notes and essays on proof systems, verifiable AI, and research in progress.
I write about proof systems, verifiable AI, and research I am trying to make clear.
Essays
- 2026-04-21
Why Documentation Structure Fits Agent Workloads
A visual essay on how curated manifests, canonical metadata, crawler boundaries, and simple health checks make documentation easier for AI agents to retrieve and cite.
- 2026-04-15
Why STARK Execution Structure Fits Transformer Workloads
A beginner-friendly explanation of why transformer decode looks like a repeated state transition, why that shape is natural for trace-based proof systems, and what the current repository artifact now shows.