In my agent fleet, role moves the metrics more than the model does — and the role mix differs per model, so pooled comparisons measure the dispatcher.
Sub-Agent Metrics Are Not Comparable to Main-Thread Metrics
Related
When DeepSeek-V4-Flash Is the Right Call: A Guide to High-Throughput LLM Calls published: true
Hey DEV — RouteAI team here, disclosure upfront. We've written about DeepSeek V4's Pro/Flash split...
Approval Is Not a Boolean: What Must Still Be True When an Agent Resumes?
Human approval is a decision about one action under a particular set of facts. It is not a permanent...
What I got wrong building a browser extension with an AI assistant
First hour with Claude's browser extension: I pointed it at our LLC registration and watched it work...