Omni Verify

Omni Verify makes Kane CLI check every promise in an AI-written post, before the post ships and again after every release. Failed promises are repaired from what Kane saw. Only campaigns that pass can publish. It caught two real drifts on my own app, Scribo. I didn't plant either. - The link lies (at publish time). Every App Store button on scribo.cc overwrites the campaign tag with ct=site-en-hero, so every install from my Threads posts would have been credited to the website. No error, just a wrong number, and my agent would have concluded Threads doesn't work and stopped posting there. I haven't checked App Store Connect numbers; this is what the tags say would happen. - The product moves on (after every release). Scribo 2.0 (October 1) turned a handwriting vocabulary app into a content learning app. Old @scribo.voca posts still promise a handwriting vocabulary notebook and keep bringing people in, who then find a different product. A real post went out through the gate: Publish to Threads unlocked only because Re-verify KR-85 passed that exact version, and then it still needed a human confirm. Promises Kane failed are saved as retired in memory/product-facts.json, and the agent refuses any draft that uses them. Before my agent learns from a post, Kane proves the funnel tells the truth. AI can write the promise. Kane checks if the product keeps it. What's next: run the audit automatically on every release, follow the user into the app on the iOS Simulator to check the paywall matches the post, and ship this as the launch gate inside Omni, my growth agent.

1. 01The OpenAI agent (gpt-5.4-mini) drafts a post from the app's real page and a Kane Explore map of the site, and turns every promise into a check: the link's campaign tag, every sentence against the page, every promised feature.
2. 02