Chronos AI: Legal and medical document chronology platform

By Colter Mahlum, Founder & CEO of Mahlum Innovations — published 2026-05-01.

Colter Mahlum architected and shipped this case study end-to-end. Mechanical engineer turned AI builder, based in Bigfork and Kalispell, Montana. 12 platforms built across healthcare, wellness, legal, wealth management, fitness, and consumer apps.

Turning complex record sets into structured, searchable patient timelines for law firms

App: Chronos AI | Industry: Legal Technology | Client: Legal document intelligence platform (designed for law firms handling medical record review) | Company size: Law firms handling personal injury, medical malpractice, and workers compensation matters | Duration: Initial build complete, ongoing development

Summary

A document chronology platform that ingests legal and medical record sets and produces structured event timelines, built on React, TypeScript, Node, and Supabase Postgres with pgvector for semantic search across document corpora.

The Challenge

Law firms handling personal injury and medical malpractice matters routinely receive hundreds to thousands of pages of medical records per case. Turning those records into a structured, searchable chronology is time-intensive attorney and paralegal work that can take days per matter and introduces inconsistency under deadline pressure.

Our Approach

Outcomes & ROI

Reduces the time from record receipt to a reviewable chronology and makes the underlying record corpus searchable by meaning rather than exact keyword match.

Technologies Used

React, TypeScript, Node.js, Supabase Postgres, pgvector, Drizzle ORM

Key Takeaways

  1. pgvector makes a document corpus searchable by meaning rather than keyword, which changes how legal teams find relevant records in large files
  2. Structured event extraction is the foundation for any downstream legal analytics. Getting the schema right early saves significant rework later
  3. Role-based access control distinguishing attorney and paralegal permissions is necessary from day one in legal tooling, not an afterthought

Frequently Asked Questions

What document formats does the platform accept?

The ingestion pipeline handles multi-format uploads including PDFs and scanned documents. Events are extracted with structured metadata including date, provider, facility, and clinical category.

How does semantic search work across medical records?

Records are embedded using pgvector in Supabase Postgres. Search queries are also embedded and matched by vector similarity, so a search surfaces relevant records even when they use different clinical terminology than the query.

Is the platform in use at law firms today?

The platform has been built and is in active development. Client onboarding is ongoing.

Related Services

About the Builder

Colter Mahlum, Founder & CEO of Mahlum Innovations
Colter Mahlum — Founder & CEO, Mahlum Innovations

Mechanical engineer turned AI builder. Colter personally architected and shipped Chronos AI end-to-end — strategy, model development, and the production MLOps work — alongside 10+ other AI systems across manufacturing, wealth management, healthcare, and consumer apps. Read full bio · LinkedIn.

More Case Studies