Spotify engineering blog

Loading
AI Product Management at Spotify: A View From Three Angles
Three Spotify principal product managers describe how the AI PM role differs across the research, foundation model, and user experience layers of the stack. They cover shaping model behavior through data and evals, proving the value of a shared recommendation model across partner teams, and designing evaluation for open-ended conversational interfaces. The post argues that core product fundamentals stay constant while AI adds layers of specialization.
Introducing: Spotify Technology. Proven at Spotify, now yours.
Spotify introduces Spotify Technology, a unified brand for its developer and R&D tools, including Portal, Xirp, Confidence, and Spotify for Backstage. The company outlines its vision for connecting organizational context, agentic development, and product intelligence across the software lifecycle.
Why Spotify Is Not Using Bayesian A/B Testing
Spotify examines why Bayesian A/B testing is not a single methodology, showing how priors, likelihoods, and stopping rules determine guarantees around peeking, false discoveries, and winner’s curse. It compares Bayesian configurations with frequentist methods and explains why Spotify continues to use frequentist tooling.
Portal by Spotify cut my Claude Code token usage by 90%
Dimitri Mazmanov explains how Spotify’s Portal modes and Claude Code hooks route bulk file reading and boilerplate generation to cheaper worker models. The shunt plugin reduced Claude Code token usage by about 90%, while the post details its routing layers, scripts, benchmarks, latency trade-offs, and limitations.
Let’s Talk Agentic Development: Spotify x Anthropic Live
This post discusses how AI agents are transforming the way we build software and how developers think about their work. It summarizes Spotify’s live session with Anthropic on agentic development, covering practical examples and the implications for developer workflows.
Our Multi-Agent Architecture for Smarter Advertising
Spotify describes the multi-agent architecture they built to improve advertising systems, emphasizing that the goal was to fix structural problems rather than to ship an "AI feature." The piece explains how multiple cooperating agents solve complex ad tasks more reliably and integrate with existing infrastructure.