I’ve tried the Agent Architect but didn’t have much luck with getting a good answer. My question related to what reasoning level and model I should use to process my payload to avoid deadline errors and it recommended GPT4o which had a harder time processing the information I was sending.
On the prompt optimizer I was thinking of something similar to OpenAI’s prompt optimizer but trained for compatibility with your Agent Studio environment and documentation for System Prompts.
It would also be useful to have a way to benchmark a prompt to quickly see the output without having to re-trigger another webhook payload. e.g. An option to replay a recent Webhook payload from recent logs.
4. Future Consideration
Model recommender, Prompt Optimizer, and Prompt benchmark for System Prompts
+4
+1
Best,
Somu Amujala
Sign up
Already have an account? Login
If you're a Moveworks customer, you can click the SSO button below to login-even if it's your first time. Everyone else can use email or click create an account above to register.
LOGIN WITH MYMOVEWORKS SSO PARTNERS WITH SSO LOGINor
Login or create an account
If you're a Moveworks customer, you can click the SSO button below to login-even if it's your first time. Everyone else can use email or click create an account above to register.
LOGIN WITH MYMOVEWORKS SSO PARTNERS WITH SSO LOGINor
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.