A Simple Prompt Engineering Experiment Template for Text Summarization

In this second video of our Prompt Engineering series, lets walk you through a systematic framework for building and experimenting with prompts to achieve better results. We'll go through a text summarization example including task definition, setting up an evaluation metric using GPT-4 as a judge to score the quality of the summaries using a 4 point criteria, create a few prompt candidates then experiment! This video is perfect for anyone looking to deepen their understanding of AI and improve their prompt engineering skills. See you there, cheers!. 📚 Chapters 00:00 - Introduction to prompt components and experimentation process 00:32 - Starting code-based experimentation with Jupyter and Python 00:58 - Example of extracting links using the CHPT API 01:59 - Evolving the application with context information 02:50 - Optimizing output with an output indicator for desired format 03:10 - Overview of prompt components for systematic experimentation 04:00 - Setting up evaluation metrics for summarizing AI papers 05:02 - Summarizing a paper and setting up the summarization engine 05:57 - Setting up the evaluation process and criteria 06:42 - Generating prompt candidates with Python 07:17 - Turning prompt ideas into a Python list for experimentation 08:41 - Setting up an experimentation table with Pandas for prompt testing 09:35 - Concluding the experimentation process and identifying the best prompt 10:38 - Closing remarks and preview of the next module on advanced prompt engineering techniques 🔗 Links: - Source code: https://github.com/EnkrateiaLucca/oreilly-prompt-eng/blob/main/notebooks/1.2-prototyping-prompts.ipynb - Subscribe!: https://www.youtube.com/channel/UCu8WF59Scx9f3H1N_FgZUwQ - Tiktok: https://www.tiktok.com/@enkrateialucca?lang=en - Twitter: https://twitter.com/LucasEnkrateia - LinkedIn: https://www.linkedin.com/in/lucas-soares-969044167/ - AI project tracker from Ben's Bites: https://bensbites.beehiiv.com/subscribe?ref=CoXhc4I0