marketing_ops · media · workflow

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.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Advertiser submits natural language brief
Advertisers generate optimized media plans through natural language interaction.
Tools used
Vertex AIGemini 2.5 ProgRPCPostgreSQLGoogle CloudApollo
Outcome

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.

What failed first

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.

Results
Time saved5-10 seconds
Volume20+
Source

https://engineering.atspotify.com/2026/02/our-multi-agent-architecture-for-smarter-advertising

How we source this →

Grounding & classification
Source type: technical build writeup
29 fields verified against source quotes, 1 dropped as unverifiable.
agentic workflowconversational aimulti agent workflowrecommendation systemknowledge basemetric backednamed customerproduction runtime claimedtools describedworkflow describedmediacycle time reductionemployee productivitytime savedtechnical build writeupmarketing opssales opsagentic task executionextract classify route