agent’s abilities, and you can diagnose where smaller models succeed or fail. In summary, the principles for choosing a model are simple: 01 Set up evals to establish a performance baseline 02 Focus handoffs that transfer execution between agents. Regardless of the orchestration pattern, the same principles apply: keep components flexible, composable, and driven by clear, well-structured prompts. 17

processes before attempting to solve the specific problem. By considering the broader and underlying principles, LLMs can generate more accurate and insightful responses. Step-back prompting encourages LLMs is prompted directly. It can help to mitigate biases in LLM responses, by focusing on general principles instead of specific details, step-back prompting. Let’s have a look into these examples to understand

serving with pagedattention. In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles, 2023. G. Lai, Q. Xie, H. Liu, Y. Yang, and E. H. Hovy. RACE: large-scale reading comprehension