Prompting the future (Practical AI #261)

Changelog Master Feed

Daniel & Chris explore the state of the art in prompt engineering with Jared Zoneraich, the founder of PromptLayer. PromptLayer is the first platform built specifically for prompt engineering. It can visually manage prompts, evaluate models, log LLM requests, search usage history, and help your organization collaborate as a team. Jared provides expert guidance in how to be implement prompt engineering, but also illustrates how we got here, and where we’re likely to go next.

Leave us a comment

Changelog++ members save 4 minutes on this episode because they made the ads disappear. Join today!

Sponsors:

• Shopify – Sign up for a $1/month trial period at shopify.com/practicalai
• Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs.

Featuring:

• Jared Zoneraich – Twitter, LinkedIn
• Chris Benson – Twitter, GitHub, LinkedIn, Website
• Daniel Whitenack – Twitter, GitHub, Website

Show Notes:

• PromptLayer

Something missing or broken? PRs welcome!

Kapitler

1. Welcome to Practical AI (00:00:07)

2. Prompt master Jared Zoneraich (00:00:43)

3. What is prompt engineering? (00:01:21)

4. Different models, different approaches (00:04:59)

5. Struggles in prompt engineering (00:07:10)

6. What it's like to use an API (00:10:03)

7. Shift in users (00:12:41)

8. Building on probabilistic technology (00:15:20)

9. Handling non-deterministic models (00:18:42)

10. Implications of changes in prompts (00:21:39)

11. Sponsor: Shopify (00:27:59)

https://www.shopify.com/practicalai

12. Optimizing prompts (00:30:35)

13. Logging and monitoring best practices (00:35:25)

14. Providing users feedback (00:38:33)

15. Future of prompt engineering (00:40:55)

16. Thank you Jared! (00:44:30)

17. Outro (00:45:12)