Tech Meridian ← LIVE FEED
PROMY MERIDIAN RU

FUNDING · CODING · #1710

Spotify presents Ads AI multi-agent production patterns using Google ADK Java

At QCon AI, Pratik Rasam (Senior Engineer, Spotify Ads) described how Spotify Ads Manager’s Ads AI runs production-grade multi-agent systems using Google ADK Java and Vertex AI on GCP. The talk covered architectural patterns, domain ownership (one agent = one package/owner), deterministic guardrails, tracing-based evaluation, and lessons on agent boundaries, tool schemas, and cost management; Spotify reported that since launch >70% of ads use AI, with ~20,000 creatives for over 7,000 advertisers.

KEY POINTS

  1. At QCon AI, Pratik Rasam (Senior Engineer, Spotify Ads) described how Spotify Ads Manager’s Ads AI runs production-grade multi-agent systems using Google ADK Java and Vertex AI on GCP.
  2. The talk covered architectural patterns, domain ownership (one agent = one package/owner), deterministic guardrails, tracing-based evaluation, and lessons on agent boundaries, tool schemas, and cost management; Spotify reported that since launch >70% of ads use AI, with ~20,000 creatives for over 7,000 advertisers.
  3. This reveals a concrete, production-scale multi-agent architecture and operational lessons from a major company, relevant for teams deploying AI systems at scale.

WHY IT MATTERS

This reveals a concrete, production-scale multi-agent architecture and operational lessons from a major company, relevant for teams deploying AI systems at scale.

SOURCES & TIMELINE

1