Marketing ops · Production

Spotify builds multi-agent Ads AI to automate media planning from 15–30 minutes to seconds

The problem

Spotify's ads platform re-implemented the same core planning decisions per buying channel and surface, causing logic to drift over time and leaving no unified intent layer to orchestrate advertiser goals consistently. Advertisers also had no optimization guidance and faced complex multi-screen configuration flows.

First attempt

Hard-coded happy paths per channel could not capture the combinatorial nature of ads planning, and freezing the probabilistic, ML-dependent ads logic into a static decision tree was recognized as brittle and unmaintainable.

Workflow diagram · grounded in source
1
Advertiser submits natural language brief
trigger
“enables advertisers to generate optimized media plans through natural language interaction”
2
RouterAgent classifies request
routing
“The RouterAgent analyzes incoming user messages and determines what information is present: This fast routing step prevents unnecessary LLM calls and enables conditional agent execution.”
3
Resolution agents extract campaign dimensions
ai_action
“GoalResolverAgent: Maps user intent to campaign objectives (REACH, CLICKS, APP_INSTALLS, etc.) and searches for appropriate ad categories AudienceResolverAgent: Extracts targeting criteria including interests (from a predefined taxonomy)…”
4
MediaPlannerAgent generates optimized recommendations
ai_action
“The MediaPlannerAgent is where the magic happens. It takes all resolved information and generates optimized ad set recommendations using a heuristics-based engine backed by historical performance data.”
5
Optimized media plan delivered
output
“generate optimized, data-driven media plans in seconds”
Reported outcome

The multi-agent Ads AI 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, grounding recommendations in historical performance from thousands of campaigns.

Reported metrics
Media plan creation time (agentic)5-10 seconds
Media plan creation time (manual baseline)15-30 minutes
Required user inputs (agentic)1-3 natural language messages
Required user inputs (manual baseline)20+
Show all 6 reported metrics
media plan creation time (agentic)5-10 seconds
media plan creation time (manual baseline)15-30 minutes
required user inputs (agentic)1-3 natural language messages
required user inputs (manual baseline)20+
agent response latency with parallel execution~3-5s with parallel execution
optimization data coverageHistorical performance from thousands of campaigns
Reported stack
Ads AIGoogle ADKVertex AIGemini 2.5 ProgRPCGoogle CloudPostgreSQLApolloRouterAgentMediaPlannerAgent
Source
https://engineering.atspotify.com/2026/2/our-multi-agent-architecture-for-smarter-advertising
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

The multi-agent Ads AI 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, grounding recommendations in histor…

What tools did this team use?

Ads AI, Google ADK, Vertex AI, Gemini 2.5 Pro, gRPC, Google Cloud, PostgreSQL, Apollo, RouterAgent, MediaPlannerAgent.

What results were reported?

Media plan creation time (agentic): 5-10 seconds; Media plan creation time (manual baseline): 15-30 minutes; Required user inputs (agentic): 1-3 natural language messages; Required user inputs (manual baseline): 20+ (source-reported, not independently verified).

What failed first in this deployment?

Hard-coded happy paths per channel could not capture the combinatorial nature of ads planning, and freezing the probabilistic, ML-dependent ads logic into a static decision tree was recognized as brittle and unmaintai…

How is this marketing ops AI workflow structured?

Advertiser submits natural language brief → RouterAgent classifies request → Resolution agents extract campaign dimensions → MediaPlannerAgent generates optimized recommendations → Optimized media plan delivered.