TikTok Ads experimentation agent

Runs a small number of TikTok copy tests at a time, one variable per test, and promotes a winner only on cost per goal.

Proposes and runs controlled tests of new TikTok targeting, so new audiences are found deliberately rather than by accident.

Uses native split tests to prove whether a different TikTok bid strategy or target actually beats the current one.

Measures how many TikTok conversions your ads truly drive and recalibrates targets with the result.

A test-and-learn loop for TikTok ads: build new image variants in Figma, Canva or Runway and new video in Runway or Google Veo from the winning angles, test each against the current best with a fixed split, and retire the losers once there is enough data. Needs a video MCP such as Runway or Google Veo connected in Roadway.