This is the clip Vanishing Gradients opens the episode on, and host Hugo Bowne-Anderson picks it straight up to ask why the design is bad. Husain's answer in the next turn is short: you cannot tell whether the agent's answer is right. He is describing the internal AI product he sees companies building more than any other.
And I have seen this product being built at companies more than any other product. Like everyone is building this. It is some kind of agent, internal agent that will answer business questions. But this is actually really bad. Do not make something like this.
Yo, so that was Hamil Hussein, ML engineer, longtime friend of the Vanishing Gradients podcast, and one of the most interesting, dare I say, AI scientists in the space. Why is the data agent everyone is building such a bad design?
You don't really know if it's right. How do you know?
Data science is back, baby. Every agent produces noisy outputs, tangled tool calls, strange human behavior, and thousands of possible paths through a system. Hamill and I trace what that means from the data agent everyone's building to a possible emerging new role, that of the AI scientist. We also…