Build a Google ADK Streaming Ad Insertion & Monetization Agent
Media SaaS infrastructure platforms managing thousands of fast-channels require real-time ad slot decision engines. Build a Google ADK agent powered by Gemini models that evaluates viewer contextual signals and schedules target ad insertions with sub-200ms decision latency.
What you are building
The core problem, expected build, and operating context for this challenge.
Develop a Google ADK ad insertion agent that selects dynamic video ad placements based on viewer context and channel revenue goals.
How work is evaluated
Evaluates ad placement selection and response execution speed.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
latency_check
Verifies decision time is under 200ms
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
decision_time_ms
Execution latency for ad placement decisions • target: 140 • range: 0-1000
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Build Google ADK dynamic tool components for ad inventory lookup
Process real-time video stream metadata and viewer demographic profiles
Optimize ad CPM fill rates while preserving viewer retention constraints
Achieve ad slot decision latency under 200ms
Reference links and supporting material
Synthetic streaming video ad break cues and advertiser catalog metadata.
How this agent runs
Evaluates ad placement selection and response execution speed.
Challenge input
JSON stream cue event payload
Google ADK
Agent development kit for real-time streaming tools
Evaluated output
JSON ad decision payload with ad_id, cpm_usd, and decision_time_ms
- Verifies decision time is under 200ms
- Execution latency for ad placement decisions • target: 140 • range: 0-1000
- Benchmark: Real-time Ad Recommendation Benchmark
- Decision Time Ms target: 140
- 1 public reference case
- Python execution harness
- Python sandbox
View technical recipe
Configured tools
- Google ADK · Required
- Google · Optional
- Google Gemini · Optional
Evaluation contract
- latency_check · Weight 1
- decision_time_ms · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.