Back to Blog
Tag
#agent-ops
2 posts
- Agent-infrastructureAgentic-coding-research
Codex Telemetry Shows the Agent Is a Runtime, Not a Chat Window
A Codex telemetry overlay with 731,341 logs and 1,180,462 spans shows where agent work actually lives: streams, turns, tool dispatch, and long-tail latency.
Michael Isaac - Agent-infrastructureAgentic-coding-research
The Agent Loop Map: Claude Code Is Mostly Search, Edit, Shell, Repeat
In 247,592 Claude Code tool events, 81.7% of tool-family transitions stayed inside the search/edit/shell core. The leverage is not just prompt engineering. It is loop-shaping.
Michael Isaac