Spotify Engineering

Spotify’s official technology blog

Sep 8, 2026 Why Spotify Is Not Using Bayesian A/B Testing Clearing the confusion about what Bayesian A/B testing is. Aug 13, 2026 When Can LLMs Replace Humans in A/B Tests? TL;DR: LLM predictions can stand in for human outcomes in A/B tests, but only by assumption, not by design.... Jul 27, 2026 Indexing the Data Lake for Online Point Queries Companies like Spotify need vast quantities of data accessible at low latency for online services and,... Jul 20, 2026 Content Ingestion & Podcast Video Incident Report Over the past two months, podcast creators have experienced a series of…

saved by

• Charlie Wong
• Raffi Hotter
• Matthew Keller

related reading

• Spotify’s New Experimentation Platform (Part 1) | Spotify Engineeringengineering.atspotify.com
• Coding Is No Longer the Constraint: Scaling Developer Experience to Teams and Agents at Spotify | Spotify Engineeringengineering.atspotify.com
• Your AI Product Needs Evals – Hamel's Blog - Hamel Husainhamel.dev
• What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
• Musings on Building a Generative AI Productlinkedin.com
• 2025: The year in LLMssimonwillison.net
• Philipp Schmid on X: "Here is how @SpotifyEng uses coding background agents for thousands of code migrations and what they learned: - Define desired verifiable end states explicitly, not strict todo steps. - Code examples improved output reliability. - Agent has access to 3 tools, verify, git and https://t.co/SlXpCk3nPt" / Xx.com
• Latent.Space | Substacklatent.space
• PostTrainBenchposttrainbench.com
• Langfuselangfuse.com
• What it Took to Scale Spotify’s Marketing Efforts | Spotify Engineeringengineering.atspotify.com
• What We Learned from a Year of Building with LLMs (Part II) – O’Reillyoreilly.com