“…you essentially run them in a near autonomous mode, and then you have another agent that's like… blows the whistle and say, no, that one you need to get permission on”
Brad Wardell · The AI Marketing Companion · AI Agents Are Draining Marketing Budgets? | Brad Wardell
Play from 11:48
11:48
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
run a second, adversarial AI agent that reviews any content an autonomous agent wants to publish and blocks it unless a human approves
Said nearby on the same subject
“When work comes in, the intake agent… preparer agent does the first draft… reviewer agent checks that draft… a person always approves before anything reaches the client.”
“If AI is ever at risk of giving them a run around, I would not want AI talking to my patients… I would want a human to do anything that could get you in any trouble.”
♫
Said on Dental Digest Podcast with Dr. Melissa Seibert
“If an agent continues to ask you for some human approval on everything, people are just going to click yes… you need to make sure you are not just letting the human hit yes without reading.”