Prompt Engineering Author: Lee Boonstra Prompt Engineering February 2025 2 Acknowledgements Content contributors Michael Sherman Yuan Cao Erick Armbrust Anant Nawalgaria Antonio Gulli Simone Cammel Grace Mollison Technical Writer Joey Haymaker Designer Michael Lanning Introduction 6 Prompt engineering 7 LLM output configuration 8 Output length 8 Sampling controls 9 Temperature 9 Top-K and top-P 29 Self-consistency 32 Tree of Thoughts (ToT) 36 ReAct (reason & act) 37 Automatic Prompt Engineering 40 Code prompting 42 Prompts for writing code 42 Prompts for explaining code 44 Prompts for

eleven charts that help illustrate observations that follow. We hope this compilation adds to the discussion of the breadth of change at play – technical / financial / social / physical / geopolitical. No are doing to illustrate trending during this uniquely dynamic time. Our goal is to add to the discussion.• Seem Like Change Happening Faster Than Ever? Yes, It Is • AI User + Usage + CapEx Growth = Unprecedented Stanford University… 1: AI ‘Winter’ was a term used by Nils J. Nilsson, the Kumagai Professor of Engineering in computer science at Stanford University, to describe the period during which AI continued to

Evaluation Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.4 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 5 Conclusion 31 D.2 Comparison Between MLA and MHA . . . . . . . . . . . . . . . . . . . . . . . . . 31 E Discussion About Pre-Training Data Debiasing 32 F Additional Evaluations on Math and Code 33 G Evaluation Supervised Fine-Tuning (SFT), Reinforcement 5 Learning (RL), the evaluation results, and other discussion (Section 4). Finally, we summarize the conclusion, deliberate on the current limitations of DeepSeek-V2

new category of LLM-powered systems known as agents. This guide is designed for product and engineering teams exploring how to build their first agents, distilling insights from numerous customer deployments 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

Frameworks New operator introduced by operator fusion optimization potential benefit: 1.5x speedup Engineering intensiveMachine Learning based Program Optimizer TVM: Learning-based Learning System High-level

Developer resources are the main bottleneck and growth inhibitor in many organizations. 
 When engineering teams are overwhelmed, it slows innovation and creates an insurmountable backlog of apps and ideas

performance, while providing high capacity and high voltage curves, has sparked in-depth research and discussion. As a promising candidate for anode materials, alloy-based anodes such as silicon (Si, 4200 mA alloy-based anodes, especially silicon (Si, 4200 mA h g-1), have sparked in-depth research and discussion. This is primarily due to their extremely high theoretical capacity, which is nearly 10 times