The Stack Overflow Podcast One is not the loneliest number for API calls
Oct 3, 2025
Gil Feig, Co-founder and CTO of Merge, delves into the future of APIs by discussing how to streamline multiple third-party integrations into a single call. He emphasizes the importance of data normalization and shares insights on the role of AI in this process. Feig also explores the challenges of chaining agent calls and the necessity for human oversight in managing AI-generated code, all while highlighting the shift towards more efficient event mechanisms like webhooks. Expect a fascinating look at balancing innovation with practical engineering skills.
AI Snips
Chapters
Transcript
Episode notes
Early Botting Sparked A Software Career
- Gil Feig started coding at 12 by building game bots and joined core library teams as a teen.
- That early experience sparked a lifelong passion for software and automation.
One Normalized Model For Many APIs
- Merge normalizes multiple third-party APIs into one opinionated data model to avoid repeated integrations.
- This model captures common objects across platforms while still exposing platform-specific features.
Opinionated Normalization Beats Exhaustive Mappings
- Opinionated means selecting a focused set of fields so APIs are broadly useful rather than sparse and unwieldy.
- Merge balances normalization with exposing unique platform fields and onboarding flows.