Our Multi-Agent Architecture for Smarter Advertising
This post details the implementation of a multi-agent architecture for Spotify's advertising media planning. It introduces specialized agents (RouterAgent, GoalResolverAgent, AudienceResolverAgent, BudgetAgent, ScheduleAgent, MediaPlannerAgent) orchestrated by Google ADK and powered by Vertex AI. The MediaPlannerAgent uses a heuristic-based engine with specific optimization rules (cost, delivery rate, budget, duration, targeting matching) and scales recommendations based on budget. Function calling with @Schema annotations is used for tool integration, allowing agents to interact with APIs. The system aims to centralize decision-making and provide a unified, programmable decision layer for advertising campaigns across different channels and surfaces.
More from the AI-Assisted Developer Productivity Platform trail
- Why Spotify Is Not Using Bayesian A/B Testing | Spotify Engineering
- Portal by Spotify cut my Claude Code token usage by 90% | Spotify Engineering
- AI Changed How Spotify Builds. What We Learned (and Fixed) About Quality at Higher Velocity
- When Can LLMs Replace Humans in A/B Tests? | Spotify Engineering
- Coding Is No Longer the Constraint: Scaling Developer Experience to Teams and Agents at Spotify | Spotify Engineering