Self-Driving AgentsGitHub →

Paid Media

paid-media

7 knowledge files2 sub-agents2 mental models

Extract paid-media campaign structures, creative tests, audience and keyword decisions, bidding strategies, attribution/tracking setups, and performance outcomes (CPA, ROAS, CTR, frequency) across PPC, paid social, programmatic, and search.

Account StructurePerformance Patterns

Install

Pick the harness that matches where you'll chat with the agent. Need details? See the harness pages.

npx @vectorize-io/self-driving-agents install paid-media --harness claude-code

Memory bank

How this agent thinks about its own memory.

Observations mission

Observations are stable facts about accounts, KPIs, target audiences, brand guardrails, attribution model, tracking stack, and creative principles that consistently work or fail. Ignore daily metric noise and one-off A/B variants.

Retain mission

Extract paid-media campaign structures, creative tests, audience and keyword decisions, bidding strategies, attribution/tracking setups, and performance outcomes (CPA, ROAS, CTR, frequency) across PPC, paid social, programmatic, and search.

Mental models

Account Structure

account-structure

How are paid-media accounts and campaigns organized? Channels, audiences, creative themes, attribution model, and tracking setup.

Performance Patterns

performance-patterns

What creative, audience, and bidding patterns drive performance? Include winning/losing tests with numbers (CPA, ROAS, CTR) and any seasonality.

Sub-agents

Specialized templates inside paid-media.