Spotify builds a multi-agent architecture for AI-powered advertising media planning
Spotify's ads business had the same core decisions re-implemented per buying channel and surface, causing behavior to drift over time with no unified intent layer to understand advertiser goals and orchestrate Ads APIs consistently. Advertisers also had to manually configure all campaign dimensions without optimization guidance from historical performance data.
The Ads AI multi-agent system reduced media plan creation time from 15-30 minutes to 5-10 seconds and cut required user inputs from 20+ form fields to 1-3 natural language messages, with every recommendation backed by historical performance data from thousands of campaigns.
The standard playbook of a new service with a state machine and REST endpoints did not fit because workflows are combinatorial and decisions needed to appear consistently everywhere. The previous manual campaign configuration had complex UI flows, no optimization guidance, slow iteration, and no access to historical performance data.
https://engineering.atspotify.com/2026/02/our-multi-agent-architecture-for-smarter-advertising