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

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 hypothetical endpoint, but as a reachable threshold. If / when achieved, AGI would redefine what software (and related hardware) can do. Rather than executing pre-programmed tasks, AGI systems would understand 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 novelty

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 your first agent. 3 A practical guide to building agents What is an agent? While conventional software enables users to streamline and automate workflows, agents are able to perform the same workflows coupled with robust authentication and authorization protocols, strict access controls, and standard software security measures. 24 A practical guide to building agents Think of guardrails as a layered defense

responsive customer experiences. 3 AI in the EnterpriseBut leveraging AI isn’t the same as building software or deploying cloud apps. The most successful companies are often those who treat it as a new paradigm a process are best-placed to improve 
 it with AI. 06 Unblock your
 developers Automating the software development lifecycle can multiply 
 AI dividends. 07 Set bold 
 automation goals Most processes 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 board. • Move hardware complexity to software HW-SW Blueprint for Flexible Deep Learning Acceleration. Moreau et al. IEEE Micro 2019. VTA Hardware/Software Interface (ISA) VTA MicroArchitecture VTA

requires careful engineering optimization to manage the GPU memory and RAM pressure, and meanwhile maintain a fast training speed. For this goal, we implement the following engineering optimizations. (1) preprint arXiv:2311.07911, 2023. 26 Appendix A. Contributions and Acknowledgments Research & Engineering Aixin Liu Bingxuan Wang Bo Liu Chenggang Zhao Chengqi Deng Chong Ruan Damai Dai Daya Guo Dejian

Terasic DE10-Nano DEPLOY VTA ON INTEL FPGA©2019 HARMAN INTERNATIONAL INDUSTRIES, INCORPORATED 5 Software - CMA Contiguous Memory Allocation – Linux Kernel DEPLOY VTA ON INTEL FPGA https://pynq.readthedocs socfpga-4.9.76-ltsi-rt_18.08.02_pr.tar.gz©2019 HARMAN INTERNATIONAL INDUSTRIES, INCORPORATED 6 Software - CMA Contiguous Memory Allocation – Linux Kernel Module DEPLOY VTA ON INTEL FPGA Setup Environment DE10-Nano and Install Module CMA API Reference©2019 HARMAN INTERNATIONAL INDUSTRIES, INCORPORATED 7 Software - Driver Cyclone V & Arria V SoC HPS Physical Memory Map DEPLOY VTA ON INTEL FPGA©2019 HARMAN

from the Arm ecosystem, through collaborative seamless integration with the ecosystem of AI/ML software frameworks and librariesArm NN open source project ● Linaro-hosted https://www.mlplatform.org/