Angelina YangFounder and Host, TwoSetAI · AI builder for visibility and discoverability

Prompting Creates Hallucinations

13 Aug 2026 · 0 min

Watch on YouTube

0:28

When users add custom prompts to an AI agent's existing instructions, it creates conflicting guidance that confuses the system. Speaker B explains how this contradiction destabilizes the agent's knowledge base, making it more likely to hallucinate or invent false information.

I think humans communicating with agents actually creates another layer of potential hallucination.
We don't let you put in a prompt. We have found that when people try to prompt on top of the context object, they oftentimes cause more issues because now you're giving differentiated advice from what the context object has. And so these systems get confused and you can actually generate more hallucinations.