Field Notes

OpenAI's Forward Deployed Engineers use eval-driven development—building measurement before demos—to make agents production-ready. A companion six-step framework describes how to build a merge gate that lets agents ship changes without human review, addressing judge bias, trajectory grading, log-mined tests, judge versioning, and blast-radius-based gating.

Cloudflare open-sourced Cloudflare OS, an internal-first platform giving every employee an agent workspace grounded in company context, with a new security/governance framework (Gatekeepers) and a system for building shareable, modifiable full-stack apps as Workers.

A LinkedIn outbound framework (used with the Gojiberry agent) combines intent signals (topics/competitor engagement) with ICP filtering, replaces cold demo asks with value-permission offers, and automates lead-finding rather than relationship-building—yielding 59%+ connection rates and 300+ demos in 30 days.

Peter Yang released /human-review, a free open-source skill that opens HTML/Markdown files in a local visual editor for direct editing, image resizing, and Google Docs-style commenting, batching all feedback to send to an AI agent at once instead of describing changes in chat.

Dan Rosenthal outlines a 7-step operational blueprint (process mapping, 25+ MCPs/CLIs, an auto-updating wiki, ~50 reusable skills, strict folder structure, team-wide access with guardrails) that lets Claude Code handle 80%+ of execution work, enabling a 20-person team to move 5x faster than larger competitors.