Richard C. Suwandi(@richardcsuwandi):In today's agents, we have many classification steps that still burn a full LLM call. This is a great write up on how we can utilize @typesafeai's Jev for those: model routing (cheap model for simple lookups, stronger one for hard debug) and auto mode (flag risky tool calls before they run).

Richard C. Suwandi

@richardcsuwandi

AI PhD @cuhksz. Co-Founder @AIDDA_institute. Co-developed OpenEvolve, Kai @driaforall for automated research & discovery. Dev ambassador @Alibaba_Qwen

Joined February 2020

422 Following 1.2K Followers

Richard C. Suwandi@richardcsuwandi

2026.09.18 18:37

In today's agents, we have many classification steps that still burn a full LLM call. This is a great write up on how we can utilize @typesafeai's Jev for those: model routing (cheap model for simple lookups, stronger one for hard debug) and auto mode (flag risky tool calls before they run).