Multi Agent AI Personas

• Explains intro, but I missed it

• Talked about having a UI that you can talk to different agents.

• Specialized agents trained on different data could talk to each other.

• How do you create a persona

• You tell the agent to behave like a persona to don't actually train it

• It's about refining a base model rather than training a new model

• AI's generally agree with you. In order to get them to critique each other we'd need to prompt them to be critical of each other.

• After an long painful interaction I've tried asking what was the prompt I should have used to have got there qiucker. However the AI often just tells me that

I already took the quickest route.

• We should be experimenting now because my CEO thinks there will be a step change in pricing.

• We tried using a single AI with a prompt telling them to assume two personas but it wasn't succesful. They didn't switch persona cleanly.

• Crew AI - already does something similar

• We have a lot of customer data we could use to make specialist AI's but we don't have legal persmission to use it.

• GDPR concerns. User data is being sent to LLM's

• Can you include a human in the loop to evaluate responses and add some reinforcement learning

• Gell Mann Amnesia Effect. When you are an expert it produces low quality content.

• How can you validate an agent?

• You have a persona that forces agents to validate their sources. This still does not eliminate false positives but reduces the probability.

• If you still have to check I don't see the value for anything that it is critical to get right

• The utility is that everyone can ask the CEO questions at the same time.

• If that frees up 10x the CEO's time and he can validate the responses in less than that, it is still net positive for the CEO's time.

• We replaced functional tests with metrics and rolled back deployments quickly when there was a problem. Perhaps you can do the same with unverified decisions.

• You'd have to apply this not only revenue metrics but also security and other dimensions that might be hard to measure.

• Can agents maintain agent generated code

• When I'm vibe coding I often ask the agent to critique and refactor the code. This could be done by another agent.

• If HR is represented by an agent this could be legally difficult.

• The agent is only an advisor the human has to be accountable

• When humans are in a room and have to come to consensus they usually make good decisions. Would the same not happen with agents?