My AI agent writes my marketing. Today I made it prove every post is true.

Description and use

AI‑generated marketing posts can contain false claims. The author built Omni Verify, which checks every promise in a draft using Kane CLI before publication.

Problem

AI‑generated marketing posts can contain false or outdated claims, leading to misleading content and incorrect attribution data.

Outcome

All new posts now pass verification before publication; the link tag bug was fixed and old misleading posts were flagged or removed.

Workflow

• Draft post with OpenAI agent
• Agent turns promises into checks
• Kane CLI runs checks in a real browser
• Agent reads results and fixes failures
• Repeat until all checks pass
• Publish button unlocks

Evidence

I spent the day at Kane CLI Hack Day by TestMu AI, so I tested my own posts with Kane CLI.

Source

The App Store button on my website changes the campaign tag. The post sends people with ct=threads-oct24, and the button replaces it with ct=site-en-hero.

Source

For the link bug, Kane failed the first draft (KR-63). The agent linked straight to the App Store with the right tag, and Kane passed it (KR-68).

Source

The agent also remembers. The three failed promises go into a memory file as "retired."

Source