AI Gen Apps
Contact

Technique

Embeddings.

Representing records as vectors so that similarity becomes something a system can compute, which is what makes retrieval and clustering work.

2 papers · Technique

August 2026ResearchAGA-11

Read and write: how memory works in the brain, and how we engineer it into AI systems

Memory is not a store but a read/write process: encode, consolidate, retrieve. This paper maps that architecture onto AI-native systems: the context window as working memory, vector and structured stores as long-term memory, embeddings as encoding, and retrieval as recall, and why designing memory first is what separates knowing a fact from having been trained on it.

Read the paper →
  1. May 2026
    Engineering
    AGA-05

    Transaction foundation models: transformer embeddings for tabular financial data

    A transaction foundation model learns from large volumes of tabular financial data to produce transformer embeddings of individual transaction rows. Fed as features into existing ML models, those embeddings raise accuracy and cut false positives on fraud detection, authorization and risk scoring.

    Luis Hasanaj · Read →
← All research