Piotr Mardziel

Apologies I forgot an important bit to print: ```python for call in recording.get().calls: print(call.stack[-1].path, call.method()) ```

> The prompting still needs to be changed in concert with the normalization. Now (for llm-based feedback) we prompt the LLM to score 0-10. If we go with fewer levels,...

Hi @DhruvinKoshiya , do you know if Bedrock models are charged at some fixed rate that can be determined from model name?