[FailMore]

Any ideas how to solve the agent's don't have total common sense problem?

I have found when using agents to verify agents, that the agent might observe something that a human would immediately find off-putting and obviously wrong but does not raise any flags for the smart-but-dumb agent.

[atarus]

To clarify you are using the "fast brain, slow brain" pattern? Maybe an example would help.

Broadly speaking, we see people experiment with this architecture a lot often with a great deal of success. A few other approaches would be an agent orchestrator architecture with an intent recognition agent which routes to different sub-agents.

Obviously there are endless cases possible in production and best approach is to build your evals using that data.

[rush86999]

Only solution is to train the issue for the next time.

Architecturally focusing on Episodic memory with feedback system.

This training is retrieved next time when something similar happens

[atarus]

Training is an overkill at this point imo. I have seen agents work quite well with a feedback loop, some tools and prompt optimisation. Are you doing fine-tuning on the models when you say training?

[rush86999]

Nope - just use memory layer with model routing system.

https://github.com/rush86999/atom/blob/main/docs/EPISODIC_ME...

[atarus]

Memory is usually slow and haven't seen many voice agents atleast leverage it. Are you building in text modality or audio as well?