Clip / AI Agents

Design principles: model-agnostic and rising with the tide

From Morgan Stanley's ALPHALAB: Multi-Agent Research Across Optimization Domains — Brendan Rappazzo · ≈3:57

States a durable design constraint for enterprise agent systems: build so improving frontier models amplify rather than obsolete your harness.

What’s in it

States a durable design constraint for enterprise agent systems: build so improving frontier models amplify rather than obsolete your harness.

Watch this moment

Clip transcript

cycles and see if we can find an improvement. Um also, we wanted to build this to be really model agnostic, so we could use any of the frontier providers or increasingly, uh you know, any open-source model. And also, we wanted to build it in a way that you know, as these models get better and better, it's not sort of consuming what we built. Like, we kind of rise with the tide of the models. And lastly, you know, really carefully think about um how do we encode sort of like our enterprise knowledge as Morgan Stanley and then our human expertise as as quant researchers.