optimizing prompt length, and evaluating a prompt’s writing style and structure in relation to the task. In the context of natural language processing and LLMs, a prompt is an input provided to the model LLM’s output. Effective prompt engineering requires setting these configurations optimally for your task. Output length An important configuration setting is the number of tokens to generate in a response creative results, try starting with a temperature of .1, top-P of .9, and top-K of 20. Finally, if your task always has a single correct answer (e.g., answering a math problem), start with a temperature of

building agents Selecting your models Different models have different strengths and tradeoffs related to task complexity, latency, and cost. As we’ll see in the next section on Orchestration, you might want 
 of models for different tasks in the workflow. Not every task requires the smartest model—a simple retrieval or intent classification task may be handled by a smaller, faster model, while harder tasks An approach that works well is to build your agent prototype with the most capable model for every task to establish a performance baseline. From there, try swapping in smaller models to see 
 if they still

Table 27 | An example of MATH. 45 PROMPT You are an expert Python programmer, and here is your task: Write a function to find the similar elements from the given two tuple lists. Your code should pass tuple(set(test_tup1) & set(test_tup2)) return (res) [DONE] You are an expert Python programmer, and here is your task: Write a python function to identify non-prime numbers. Your code should pass these tests: assert % i == 0: result = True return result [DONE] You are an expert Python programmer, and here is your task: Write a function to find the largest integers from a given list of numbers using heap queue algorithm

dramatically reduced search time; and advisors spend more time on client relationships, thanks to task automation and faster insights. The feedback from advisors has been overwhelmingly positive. They’re internal evaluation by experts across domains, deep research saved an average of 4 hours per complex task. For more detail, watch BBVA puts AI into the hands of every team. 17 AI in the EnterpriseLesson

Adaptation（适应）：根据AI反馈动态调整任务结构 为了更有效地进行任务分解，可以采用SPECTRA模型（Systematic Partitioning for Enhanced Cognitive Task Resolution in AI）： �基于SPECTRA模型的提示语链设技巧： 1. 分割提示：“将[总任务描述]分解为3—5个主要组成部分，确保每个 部分都是相对独立但与整体目标相关的。” 1. TASTE框架 • Task (任务): 定义模型主要任务或生成内容。 • Audience (目标受众): 明确说明目标受众。 • Structure (结构): 为输出的内容提供明确的组织结 构，包括段落安排、论点展开顺序或其他逻辑关系。 提供目前的环境问题的背景，讨论应对全球变暖的 策略。 • Guidelines: 文章应使用简洁明了的语言，并避免复杂的 技术概念。 • Novelty: 要求结合最新的环境数据，提出新颖的观点和解 决方案。 示例 • Task: 写一篇关于数据隐私的重要性的简短博客文章。 • Audience: 普通的互联网用户，非技术背景。 • Structure: 文章需要有明确的开头、中间讨论和结尾， 开头提出问题，中间介绍原因和影响，结尾提供建议。

Adaptation（适应）：根据AI反馈动态调整任务结构 为了更有效地进行任务分解，可以采用SPECTRA模型（Systematic Partitioning for Enhanced Cognitive Task Resolution in AI）： �基于SPECTRA模型的提示语链设技巧： 1. 分割提示：“将[总任务描述]分解为3—5个主要组成部分，确保每个 部分都是相对独立但与整体目标相关的。” 1. TASTE框架 • Task (任务): 定义模型主要任务或生成内容。 • Audience (目标受众): 明确说明目标受众。 • Structure (结构): 为输出的内容提供明确的组织结 构，包括段落安排、论点展开顺序或其他逻辑关系。 提供目前的环境问题的背景，讨论应对全球变暖的 策略。 • Guidelines: 文章应使用简洁明了的语言，并避免复杂的 技术概念。 • Novelty: 要求结合最新的环境数据，提出新颖的观点和解 决方案。 示例 • Task: 写一篇关于数据隐私的重要性的简短博客文章。 • Audience: 普通的互联网用户，非技术背景。 • Structure: 文章需要有明确的开头、中间讨论和结尾， 开头提出问题，中间介绍原因和影响，结尾提供建议。

demand for compute. We’re seeing it across every layer: more queries, more models, more tokens per task. The appetite for AI isn't slowing down. It’s growing into every available resource – just like lower-cost API providers and achieve functionally similar results, especially when fine-tuned on task-specific data. This shift is weakening the pricing leverage of model incumbents and leveling the consultation, but also doing the work for our merchants is a mind-blowing step function change here. Our task here at Shopify is to make our software unquestionably the best canvas on which to develop the best

• 深度思考（R1）：目标清晰，结果可以模糊（推理） RTGO提示语结构 Role（角色） 定义AI的角色： 经验丰富的数据分析师 具备十年销售经验的SaaS系统商务 …… Task（任务） 具体任务描述： 写一份关于XXX活动的小红书宣推文案 写一份关于XX事件的舆论分析报告 （XX活动/事件相关背景信息如下……） Goal（目标） 期望达成什么目标效果： 通过该文案吸引潜在客户，促成消