--- schema: 1 type: video title: How to Win With Prompt Engineering - Ep. 38 with Jared Zoneraich description: >- Prompt engineering matters more than ever. But it’s evolving into something totally new: A way for non-technical domain experts to solve complex problems with AI. I spent an hour talking to prompt wizard Jared Zoneraich, cofounder and CEO of PromptLayer, about why the death of prompt engineering is greatly exaggerated. And why the future of prompting is equipping non-technical experts with the tools to manage, deploy, and evaluate prompts quickly. We get into: - His theory around why the “irreducible” nature of problems will keep prompt engineering relevant - Prompt engineering best practices around prompts, evals, and datasets - Why it’s important to align your prompts with the language the model speaks - How to run evals when you don’t have ground truth - Why he believes that the companies who have domain experts to scope out the right problems will win in the age of gen AI This is a must-watch for prompt engineers, people interested in building with AI systems, or anyone who wants to generate predictably good responses from LLMs. If you found this episode interesting, please like, subscribe, comment, and share! Want even more? Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free. To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps: 00:00:00 - Episode start 00:01:08 - Introduction 00:09:54 - Jared's hot AGI take 00:11:49 - An inside look at how PromptLayer works 00:15:44 - How AI startups can build defensibility by working with domain experts 00:25:39 - Everything Jared has learned about prompt engineering 00:29:46 - Best practices for evals 00:32:42 - Jared's take on o-1 00:39:07 - How AI is enabling custom software just for you 00:42:02 - The gnarliest prompt Jared has ever run into 00:46:39 - Who the next generation of non-technical prompt engineers are Links to resources mentioned in the episode: Jared Zoneraich: @imjaredz PromptLayer: @promptlayer, https://www.promptlayer.com/ A couple of Steven Wolfram’s articles on ChatGPT: What Is ChatGPT Doing … and Why Does It Work?, ChatGPT Gets Its “Wolfram Superpowers”! canonical: >- https://liquidgold.cc/channel/everyinc/explore/video/how-to-win-with-prompt-engineering-ep-38-with-jared-0649ae182ec0 markdown: >- https://liquidgold.cc/channel/everyinc/video/how-to-win-with-prompt-engineering-ep-38-with-jared-0649ae182ec0.md llms: null parent: 'https://liquidgold.cc/channel/everyinc.md' channel: everyinc updated: '2026-10-24T01:10:48.598Z' language: null children: [] videoId: exzPO4hAD9s durationSeconds: 3729 publishedAt: '2024-11-13T15:11:38.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 86 endSeconds: 186 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=86' heldReason: rights - ordinal: 1 text: null startSeconds: 86 endSeconds: 186 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=86' heldReason: rights - ordinal: 2 text: null startSeconds: 724 endSeconds: 951 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=724' heldReason: rights - ordinal: 3 text: null startSeconds: 951 endSeconds: 961 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=951' heldReason: rights - ordinal: 4 text: null startSeconds: 1368 endSeconds: 1379 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=1368' heldReason: rights - ordinal: 5 text: null startSeconds: 1379 endSeconds: 1497 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=1379' heldReason: rights - ordinal: 6 text: null startSeconds: 1509 endSeconds: 1541 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=1509' heldReason: rights - ordinal: 7 text: null startSeconds: 1541 endSeconds: 1552 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=1541' heldReason: rights - ordinal: 8 text: null startSeconds: 1552 endSeconds: 1791 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=1552' heldReason: rights - ordinal: 9 text: null startSeconds: 1791 endSeconds: 1802 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=1791' heldReason: rights - ordinal: 10 text: null startSeconds: 1976 endSeconds: 2075 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=1976' heldReason: rights - ordinal: 11 text: null startSeconds: 446 endSeconds: 524 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=446' heldReason: rights - ordinal: 12 text: null startSeconds: 2540 endSeconds: 2809 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=2540' heldReason: rights - ordinal: 13 text: null startSeconds: 327 endSeconds: 434 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=327' heldReason: rights - ordinal: 14 text: null startSeconds: 2361 endSeconds: 2528 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=2361' heldReason: rights - ordinal: 15 text: null startSeconds: 3371 endSeconds: 3474 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=3371' heldReason: rights - ordinal: 16 text: null startSeconds: 2917 endSeconds: 2999 watch: 'https://liquidgold.cc/watch/exzPO4hAD9s?t=2917' heldReason: rights --- # How to Win With Prompt Engineering - Ep. 38 with Jared Zoneraich Prompt engineering matters more than ever. But it’s evolving into something totally new: A way for non-technical domain experts to solve complex problems with AI. I spent an hour talking to prompt wizard Jared Zoneraich, cofounder and CEO of PromptLayer, about why the death of prompt engineering is greatly exaggerated. And why the future of prompting is equipping non-technical experts with the tools to manage, deploy, and evaluate prompts quickly. We get into: - His theory around why the “irreducible” nature of problems will keep prompt engineering relevant - Prompt engineering best practices around prompts, evals, and datasets - Why it’s important to align your prompts with the language the model speaks - How to run evals when you don’t have ground truth - Why he believes that the companies who have domain experts to scope out the right problems will win in the age of gen AI This is a must-watch for prompt engineers, people interested in building with AI systems, or anyone who wants to generate predictably good responses from LLMs. If you found this episode interesting, please like, subscribe, comment, and share! Want even more? Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free. To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps: 00:00:00 - Episode start 00:01:08 - Introduction 00:09:54 - Jared's hot AGI take 00:11:49 - An inside look at how PromptLayer works 00:15:44 - How AI startups can build defensibility by working with domain experts 00:25:39 - Everything Jared has learned about prompt engineering 00:29:46 - Best practices for evals 00:32:42 - Jared's take on o-1 00:39:07 - How AI is enabling custom software just for you 00:42:02 - The gnarliest prompt Jared has ever run into 00:46:39 - Who the next generation of non-technical prompt engineers are Links to resources mentioned in the episode: Jared Zoneraich: @imjaredz PromptLayer: @promptlayer, https://www.promptlayer.com/ A couple of Steven Wolfram’s articles on ChatGPT: What Is ChatGPT Doing … and Why Does It Work?, ChatGPT Gets Its “Wolfram Superpowers”! Canonical: https://liquidgold.cc/channel/everyinc/explore/video/how-to-win-with-prompt-engineering-ep-38-with-jared-0649ae182ec0 · Channel: [Every](https://liquidgold.cc/channel/everyinc.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks > Missing: no stored document chunks are available.