How long has the long-term memory been engineered for?

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

AI That Briefs You: The Future of Decision-Making with Long-Term Memory

26 Nov 2025 · 1 min

Watch on YouTube

0:48

This talk argues that providing people with the right information at the right time—via AI briefings grounded in long-term memory—will substantially improve decision-making. The speaker outlines a system combining long-term memory, an inference/decision engine, and agent frameworks so agents can execute with context-aware information; they note the memory work has been engineered for about two years.

Questions this video answers

About two years.

Chapters

Our thesis is that if people have the right information at the right time, their decision making would be much better, much more accurate, and much more powerful eventually in the future. We want AI to brief people in the right context. When you are making decision, AI tells you, hey, in your team, your teammate A once said this thing, your teammate B wants this thing. So when you are making decision, take those information into account. Now, the whole thing combines long term memory and decision making, inference engine and this whole agent framework. So agents can make execution and everything is based on long term memory to give them. To be able to give them the context, the right information. And this long term memory is actually something that we have been engineering for designing for for the past two years.