Field Notes · Vantage Perspectives

Show Your Work: What is Takes to Trust a Machine

A partner is about to lean on an AI-drafted memo to help decide whether to put millions into a company. Everything about that moment turns on a question the industry has trained us not to ask: how did the machine get here? This essay is about the machinery we built so that question always has an answer.

Ben WaldSEP 6 202610 MIN READ

All Portfolio Intelligence LP Relations Market Context Platform Notes Field Notes

3 ARTICLES

05Field Notes

AI Model Temperature: What it is and What it means for Judgment

Every AI agent runs at a temperature. Here is what that means, why it matters, and how each Vantage agent gets its own.

Ben WaldSEP 6 20269 MIN READ

05Field Notes

Why Our Agents Have No Reward Function: Score Everything, Optimize Nothing

We score every claim our agents make. We deliberately never let a score change an agent's behavior without a person in between. The gap between those two sentences is the most consequential design decision in the fleet.

Ben WaldJUL 29 202613 MIN READ