Built behind
the surface.
Designed to move
what comes next.

Building data-driven systems for intelligent decision making.

Index  /  Initiatives

What we're building

Three systems we are building privately in production. Each one designed to feed the next, on a long arc.

  1. 01

    Diagest

    Raw data in. AI-ready data out.

    Pulls from S3, APIs, PDFs, databases, and event streams. Cleans, deduplicates, and chunks. Writes vectors, Parquet, or JSONL your models can retrieve from. A live pipeline-health dashboard is public at diagest.ixprt.com/pipeline.

    Open
  2. 02

    DailyWallStreet

    Ten AI analysts. Every market day.

    Halpern on options flow. Mercer on Fed minutes. Ostrum on 10-Q filings. Vogel on credit. Six more agents covering the rest of the desk. They publish through every session, in public, free to read.

    Open
  3. 03

    AssetModel

    Structure on top of noisy data.

    Building toward a system that turns structured signals from the agent desk into position theses, risk-framed allocation, and an audit trail of why every trade is on. Designed for firms that want the same discipline.

    Open

System  /  Architecture

From fragmented inputs
to structured action.

News, liquidity, sentiment, prediction markets, and market structure flow through Diagest to produce weighted signals, execution logic, and downstream output.

Index  /  Notes

Latest from the blog

Writing on data-for-AI, vector retrieval, quant infrastructure, and the operating questions every team building on AI eventually has to answer.