13 posts
Content Ingestion & Podcast Video Incident Report Over the past two months, podcast creators have experienced a series of reliability issues on Spotify. This report covers the most significant of these, the June 24 publishing delay, in full detail and describes the broader relia…
Encoding Your Domain Expert: The Context Layer Behind Spotify's Data Assistant At Spotify, data problems used to follow a specific pattern. You'd look for the relevant dashboard, there weren't any. You'd message the corresponding data expert on Slack, wait until they had time to…
Coding Is No Longer the Constraint: Scaling Developer Experience to Teams and Agents at Spotify What happens when coding stops being the bottleneck? At Spotify, we’re starting to find out. Niklas Gustavsson, Spotify’s Chief Architect and VP of Engineering, recently shared how ou…
Building a Natural Language Interface to the Spotify Ads API with Claude Code Plugins We built a suite of skills, agents and tools bundled as a plugin to make the Spotify Ads Platform easily accessible to AI agentic tools. The spotify-ads-api plugin is available on GitHub and th…
Better Experiments with LLM Evals — A funnel, not a fork TL;DR LLM evals, automated judges that assess relevance, coherence, and quality at scale, are a powerful new tool. Paired with online experiments, they raise the hit rate of what we test and create a feedback loop that mak…
Background Coding Agents: Supercharging Downstream Consumer Dataset Migrations (Honk, Part 4) This is part 4 in our series about Spotify's journey with background coding agents (internal codename: “Honk”) and the future of large-scale software maintenance. See also part 1, part…
Let’s Talk Agentic Development: Spotify x Anthropic Live AI agents are transforming the way we build — and even how we think of ourselves as software developers. Both Spotify and Anthropic have been exploring what this shift means in practice, and on March 30, we got together at…
Why We Use Separate Tech Stacks for Personalization and Experimentation Introduction Personalized apps have become essential for improving user experience across diverse user bases. Rather than providing a one-size-fits-all experience for the “average user,” personalization deli…
Background Coding Agents: Predictable Results Through Strong Feedback Loops (Honk, Part 3) This is part 3 in our series about Spotify's journey with background coding agents (internal codename: “Honk”) and the future of large-scale software maintenance. See also part 1 and part…
Congratulations to the recipients of the 2025 Spotify FOSS Fund TL;DR Established in 2022 as a way to help support the great open source ecosystem projects that Spotify relies on and that our developers love, the Spotify FOSS Fund provides monetary support to projects that under…
Inside the Archive: The Tech Behind Your 2025 Wrapped Highlights Every year, Spotify Wrapped gives hundreds of millions of listeners a snapshot of your year in listening. For 2025 Wrapped, we wanted to go deeper. What if we could identify interesting listening moments from your…
How We Release the Spotify App: A Look Under the Hood (Part 2) Introduction In Part 1 of “How We Release the Spotify App”, we gave an overview of how the Spotify release process works. In Part 2, we will peek under the hood at the tooling that makes it possible. To understand wh…
Our Multi-Agent Architecture for Smarter Advertising Introduction When we kicked this off, we weren’t trying to ship an “AI feature.” We were trying to fix a structural problem in how our ads business actually runs in software. On the business side, we have multiple ways of buyi…