First run:Run the plugin mock lab, then invoke this agent in mock-run mode with the generated evidence bundle.
Setup required
Install all declared agent, skill, and tool dependencies, preferably through the ChatGPT Advertising Experiment Plugin.
Configure mock or live read-only tool bindings and a governance profile.
Current limits
The supervisor is advisory and does not execute campaign writes.
Classification: declared
Operational Summary
Role: Experiment supervisor for task-led conversational advertising and agent-mediated commerce.
Autonomy level: advisory
Approval boundary: May plan, inspect approved read-only data, and reconcile supplied evidence; live campaign writes require the existing policy gate, executor, and human approval.