Podcast
From Notebook to Production: Building End-to-End AI Systems
Open original DataTalks.Club episode
From Notebook to Production: Building End-to-End AI Systems
Original Episode
Use these links for the canonical episode and media sources.
- Open the original DataTalks.Club podcast page
- Watch on YouTube
- Listen on Spotify
- Listen on Apple Podcasts
People
Use these links to connect the episode to guest notes.
Chapter Summary
Use these checkpoints to decide whether to open the source transcript.
- 0:00 - Community Introduction and Slack Engagement
- 4:17 - Career Journey: From Argentina to Barcelona
- 7:18 - Product-Driven AI vs. Traditional Reporting
- 9:41 - AI Media Solutions for E-Commerce Sellers
- 10:58 - Video-to-Ad: The Future of Marketplaces
- 13:51 - Automated Content Creation for Sellers
- 17:27 - Defining End-to-End Ownership in Data Science
- 21:12 - The Longevity of the CRISP-DM Framework
- 25:35 - Impact of Agentic Coding and GitHub Copilot
- 31:42 - Why LLMs Aren’t Always the Best Solution
- 37:39 - Translating Business Needs to ML Requirements
- 41:28 - Managing Explicit and Implicit Feedback Loops
- 48:26 - Architecture Deep Dive: Image Description Logic
- 55:28 - The Declining Role of Notebooks in Production
- 1:02:53 - The Modern Tech Stack: Fast API, UV, and Arize