Hedge fund research · Global · via New Value Solutions

A $26Bn Hedge Fund

Agentic research validation in a $26Bn portfolio context — days of gather compressed toward hours of focus.

Head of AI / delivery leadership

The company story

A global hedge fund with roughly $26Bn AUM needed thesis validation to move at the speed of the market — across more sources — without losing rigor. Through New Value Solutions, we helped design and deliver the agentic research system.

Research cycle focus

Days → hours

Cycle

Days → hours

Architecture

Multi-agent

Context

$26Bn AUM

A $26Bn Hedge Fund — impact snapshot

Gather time returned to judgmentDays → hours
Traceable agentic researchIn place
Regulated Azure deliveryShipped

The pressure

What was on the line

Research cycles were constrained by time and source coverage. Thesis validation needed to move from days of gathering toward hours of focus while preserving signal quality the investment process could trust.

What changed

The arc of the work

  1. 01

    Decompose the research problem

    Investment theses were broken into validation paths an agentic system could run — so coverage expanded without turning analysts into prompt engineers.

  2. 02

    Orchestrate agents and evidence

    A tools-first multi-agent research architecture (including GPT-4, Claude, and Gemini) with traceable reasoning — so analysts could see how a thesis was checked, not just a score.

  3. 03

    Return time to judgment

    The win was not “more AI.” It was analysts spending less time gathering and more time deciding — with research cycles compressed from days toward hours.

Before and after

What people could feel in the week

Thesis validation measured in days of gather

Validation support oriented to hours of focused review

Source coverage limited by human bandwidth

Agentic loops expand what analysts can check

Where they are now

The outcome that stuck

In a $26Bn portfolio context, the research team keeps the judgment; the system carries the gather-and-check load. Delivery landed as a regulated Azure install through New Value Solutions.

For technical readers

How it was built

Multi-model architecture (GPT-4, Claude, Gemini), multi-agent research orchestration with LangChain/LangGraph, thesis decomposition and validation, FastAPI, Azure, PostgreSQL, Redis. Delivered through New Value Solutions.

LangGraph · GPT-4 / Claude / Gemini · FastAPI · Azure · PostgreSQL · Redis

Talk architecture and roadmap

Tell us where the product or technical load sits — we will point you to a clear next step.