My AI agent writes my marketing. Today I made it prove every post is true.
I build an app called Scribo by myself. To save time, I let an AI agent write my marketing posts. It's fast. But today I noticed something. It never checks if what it says is true. I spent the day at Kane CLI Hack Day by TestMu AI, so I tested my own posts with Kane CLI. I found two problems, and both were on my own app. The link that told the wrong story My agent wrote a Threads post and linked…
The author built an app called Scribo that uses an AI agent to write marketing posts, aiming to save time. However, the author discovered two issues with the AI agent's output. First, the AI agent did not verify the accuracy of the links or promises made in the posts, which could lead to misleading data and potentially prevent the post from being published.
Second, the author's old posts, which contained outdated information, were still being found and displayed incorrectly in app stores. To address these issues, the author created Omni Verify, a system that acts as a gate between the AI agent and the publish button. This system checks every promise made in the post, such as links and features, using Kane CLI, a browser-based testing tool.
If any checks fail, the agent is prompted to revise the post until all checks pass. This ensures that the posts are accurate and truthful before they are published, protecting both the author's reputation and the integrity of the data collected from the posts.
Brief written by urgent.news from Dev.to's own syndicated text. Machine-written — may contain errors; check the original before relying on it.
