“The problem is at human speed, this was still okay because we would fill in the gaps ourselves, right? … The delta today is, and it's a really important delta, that an autonomous agent, if it doesn't have access to the right information, cannot give you that information.”
The Data Exchange with Ben Lorica · AI Research & Frontier Labs · November 2026
Context
She was explaining why the lag of data warehouses is a bigger problem for agents than it was for people. A human support rep can look up an order in the live system, but an autonomous agent can't unless it is wired to the live data.
Transcript
…argue with you that real-time pipelining and sub-minute blah, blah, blah will give you that, but it doesn't. And like all of your listeners who've ever done this know that it's not true, right? So you use the analytics style capabilities to run sort of real-time-ish workloads and that doesn't work.
There's always going to be a lag, right? So
there's always going to be a lag. And the problem is at human speed, this was still okay because we would fill in the gaps ourselves, right? Like I think this is the biggest thing that people are now sort of facing in real time, right? Like they're realizing as they build autonomous agents that some of that lag, when the human was the operator, you could, we can fill in, right? We can go look up Salesforce and give you an answer if you're sitting in a boardroom, or we can like the customer support example that you're saying, that the…
And now if you have
autonomous decision-making agent, like how much marketing spend to have, right? Who is which microtransaction and financial services to actually let go? Like those things, you cannot intervene, right?
But still, so why does federation work now?
More from The Data Exchange with Ben Lorica
