Pulling GPT-6 Astra out of the agent workflow made it work better
The author rebuilt their Astra agent so routing, context filling and safety checks run as deterministic code, leaving the model only the hard parts, which meant fewer calls and more predictable failures.
i rebuilt my GPT-6 Astra agent after realizing the model was doing jobs the system should have handled the first version looked smart every request went straight into Astra simple routing decision? Astra missing context? Astra safety check? Astra again it worked, but the expensive reasoning layer was slowly becoming the entire architecture so i pulled those decisions out one by one the router started checking what changed before calling the model missing context got resolved before the task reached it deterministic paths handled anything that didn’t need reasoning risk checks happened separately Astra was left with the part i actually needed Astra for the weird thing was that removing the model from more of the workflow made the agent feel better fewer unnecessary calls cleaner context more predictable failures and when Astra finally ran, it was solving the difficult part instead of deciding which folder to open that changed how i think about building agents the smartest model shouldn’t be everywhere in the system the architecture should make sure GPT-6 Astra only has to be smart where being smart actually matters
This post quotes another post: x.com/lummox_eth/status/2100288151897981255