Capturing prompts in AI telemetry is a privacy decision, not a setting
AI coding tools can export prompts, tool arguments and full API bodies. Why it's off by default, the risks of switching it on, and how to decide.
Claude Code, Codex, Gemini CLI, Copilot, Cursor and the tools developers use every day.
AI coding tools can export prompts, tool arguments and full API bodies. Why it's off by default, the risks of switching it on, and how to decide.
New coding-agent benchmarks show one model scoring and costing very differently across agent harnesses. What that means for evaluating AI coding tools.
3 min read
Claude Code and Codex both ship operating-system sandboxes for agent commands. What they restrict, what runs outside them, and settings worth enforcing.
4 min read
Cached input costs a tenth of the normal price on major APIs. How prompt caching works, why coding agents depend on it, and how to see whether yours hits.
4 min read
Claude Code, Codex and Copilot now emit OpenTelemetry. What the GenAI conventions cover, what the tools actually send, and how to start measuring.