ROUTEAgents & automation
Jev for SRE Agent Reliability
Jackson Clark@HacksonClark
This project investigates whether a small, fast decision model, specifically Jev, can enhance the reliability of SRE agents when tested on SREGym-Lite problems.
Can a small and fast decision model make SRE agents more reliable? 🤔
We gave an agent access to @typesafeai’s Jev through the Codex harness and tested it on 10 SREGym-Lite problems.
Three findings stood out. More details in the thread. 🧵