Building trusted AI products

on YouTube ↗55m

" summary

Workshop walks through the updated PAIR guidebook and a live recommendation codelab that trains models (MovieLens, IMDb) and fine‑tunes BERT for sentiment, shows the language interpretability tool and Facets, and demos ordering recommendations by score, confidence displays, and immediate user feedback that removes items. Claims are concrete: a second edition with design patterns, code labs and tool links; the example movie app is built and works as a simplified demo.

AI-written summary · about

" chapters (26)

1. 0:00Introduction
2. 0:45What is the Pear Guide Book
3. 4:07Chapter Updates
4. 5:35Case Studies
5. 6:30Workshop Resources
6. 7:22User Need
7. 9:46Patterns
8. 15:33Early good data practices
9. 19:13Embrace noisy data
10. 20:58Maintain the data set
11. 26:58Create realistic data
12. 27:31Recommendations course
13. 28:23Recommendation Systems course
14. 29:11User Experience
15. 31:38Design Patterns
16. 32:12Setting the right expectations
17. 33:52Explaining the benefits
18. 35:25Explaining recommendations
19. 41:00Recap
20. 41:56Model Confidence
21. 44:49Errors
22. 46:07Examples of errors
23. 48:40Let users give feedback
24. 50:00What action will be taken
25. 50:56Example
26. 52:15Summary

" related talks

• 31mA more human-centered approach to AIJess Holbrook · Big Data & AI Toronto 2020
• 20mBridging the gap between AI and UILiad Magen · WeAreDevelopers AI Congress Vienna 2018
• 03mShowreelPyData Warsaw 2019
• 01h 21mUnlocking Personalization: A Deep Dive into Modern Recommendation AlgorithmsSarang Gupta · DSC Europe 24
• 34mInterpretable AI or How I Learned to Stop Worrying and Trust AIAjay Thampi · PyData London 2019
• 27mBuilding AI applications: Successes and LessonsTobias Kluge · Uphill Conf 2024
• 46mBeyond Bag of Words A Practitioner’s Guide to Advanced NLPAriel M’ndange-Pfupfu, Marc Anderson · PyData DC 2016
• 26mWelcome to the AI Jungle! Now What?Cedric Clyburn, Taylor Smith · ConFoo 2025