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 (CoT) 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

serve a much larger batch size. We evaluate the generation throughput of DeepSeek-V2 based on the prompt and generation length distribution from the actually deployed DeepSeek 67B service. On a single node per second, which is 5.76 times the maximum generation throughput of DeepSeek 67B. In addition, the prompt input throughput of DeepSeek-V2 exceeds 100K tokens per second. 4. Alignment 4.1. Supervised Fine-Tuning an instruction-following evaluation (IFEval) (Zhou et al., 2023) for DeepSeek-V2 Chat (SFT), using prompt-level loose accuracy as the metric. Moreover, we employ LiveCodeBench (Jain et al., 2024) questions

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 customer service for example, routines can roughly map to individual articles in your knowledge base. Prompt agents to break 
 down tasks Providing smaller, clearer steps from dense resources 
 helps minimize like o1 or o3-mini, to automatically generate instructions from existing documents. Here’s a sample prompt illustrating this approach: Unset 1 “You are an expert in writing instructions for an LLM agent.

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 would understand goals, generate plans, and self-correct in real time. They could drive research, engineering, education, and logistics workflows with little to no human oversight – handling ambiguity and databases. Model development = frameworks for modeling & training, inference optimization, dataset engineering, & model evaluation. Application development = custom AI-powered applications (varied use cases)

Global AI Adoption Product Note: With deep research, ChatGPT can do work independently. Give it a prompt, and it can synthesize hundreds of online sources to create comprehensive, PhD-level reports. This 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

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

. . . . . . . 12 2.5.5 可视化 AI 提示语 . . . . . . . . . . . . . . . . . . . . . . . 12 2.5.6 Snack Prompt . . . . . . . . . . . . . . . . . . . . . . . . 12 2.6 AI 大模型 . . . . . . . . . . . . . . . . . 提示语的工具。 2.5.5 可视化 AI 提示语 Figure 9: 可视化提示词 网址：https://tools.saxifrage.xyz/prompt，一个可视化工具，帮助用户为多 种 AI 模型生成和优化提示语。 2.5.6 Snack Prompt 提供最新 AI 模型提示词的工具，旨在快速获取和使用最新的 AI 提示进行内容 创作。 2.6 AI 大模型 2.6.1 AgentGPT

"设计一款智能家居产品，要求： ① 解决独居老人安全问题； ② 结合传感器网络和AI预警； ③ 提供三种不同技术路线的原型草图说明。" �实战技巧： 还要不要学提示语？ 提示语（Prompt）是用户输入给AI系统的指令或信息，用于 引导AI生成特定的输出或执行特定的任务。简单来说，提示语 就是我们与AI“对话”时所使用的语言，它可以是一个简单的问 题，一段详细的指令，也可以是一个复杂的任务描述。 提示语链的概念与特征 提示语链是用于引导AI生成内容的连续性提示语序列。通过将复 杂任务分解成多个可操作的子任务，确保生成的内容逻辑清晰、 主题连贯。从本质上看，提示语链是一种“元提示”（meta-prompt） 策略，它不仅告诉AI“做什么”，更重要的是指导AI“如何做”。 提示语链的设计和应用建立在多个理论基础之上，包括认知 心理学、信息处理理论、系统理论、创造性思维理论和元认 知理论，核心特征包括：

"设计一款智能家居产品，要求： ① 解决独居老人安全问题； ② 结合传感器网络和AI预警； ③ 提供三种不同技术路线的原型草图说明。" �实战技巧： 还要不要学提示语？ 提示语（Prompt）是用户输入给AI系统的指令或信息，用于 引导AI生成特定的输出或执行特定的任务。简单来说，提示语 就是我们与AI“对话”时所使用的语言，它可以是一个简单的问 题，一段详细的指令，也可以是一个复杂的任务描述。 提示语链的概念与特征 提示语链是用于引导AI生成内容的连续性提示语序列。通过将复 杂任务分解成多个可操作的子任务，确保生成的内容逻辑清晰、 主题连贯。从本质上看，提示语链是一种“元提示”（meta-prompt） 策略，它不仅告诉AI“做什么”，更重要的是指导AI“如何做”。 提示语链的设计和应用建立在多个理论基础之上，包括认知 心理学、信息处理理论、系统理论、创造性思维理论和元认 知理论，核心特征包括：

4090加载7层（共4卡） PARAMETER num_ctx 2048 PARAMETER temperature 0.6 TEMPLATE "<｜end▁of▁thinking｜>{{ .Prompt }}<｜end▁of▁thinking｜>" ollama create DeepSeek-R1-UD-IQ1_M -f DeepSeekQ1_Modelfile ollama run DeepSeek-R1-UD-IQ1_M