← CasesCS-03AI automation

AI document review pipeline.

The associate stops reading 200 pages to find three problematic clauses.

Status

In production

Sector

Legal · Corporate firm

Client

Corporate law firm · MX

Year

2026

Hook ─ Position

Premium legal work isn't reading documents — it's deciding on them. AI doesn't replace the lawyer; it gives back the time lost on mechanical review.

Demo interactivo · sandbox del despacho
─ RevisiónSelecciona un contrato
Ready

Elige un contrato y mira al sistema operar.

Pipeline real · salidas guionadas para demo

Demo en sandbox · sin contratos reales · 14 categorías configurables

Theory ─ How we think

AI automation fails when it replaces professional judgment. It works when it gives the professional back the time spent on mechanical review so they can focus on what actually requires judgment.

  1. 01

    Taxonomy defined by partners, not by the model

    The 14 risk categories were defined by partners across 3 sessions. The model never decides what risk is — only finds it.

  2. 02

    Deterministic pipeline, not open agent

    Ingest → split by clause → parallel analysis → consolidation. Every step is auditable. No step is 'a conversation'.

  3. 03

    Exact citation, always

    Every flag includes the full clause, page number, exact position. The lawyer verifies in 10 seconds what used to take 30 minutes to read.

  4. 04

    The lawyer always signs

    The system doesn't deliver results to the client. It delivers a report that the lawyer reviews, edits, and signs. Responsibility never changes hands.

Visual ─ Architecture

Ingest · Split · Analysis · Synthesis.

Cliente · 01

Internal portal

upload · SSO auth

Core · 02

Splitter

clause by clause

Servicio · 03

AI agents

14 parallel categories

Persistencia · 04

Report

signable markdown

─ Flujo del sistema

The associate uploads the contract. The system segments it by clause and fires 14 parallel analyses (one per risk category). Results consolidate into a markdown report the lawyer can edit before signing.

Practice ─ Delivery

How it shipped.

Time per contract

−72%

sustained average over 3 months

Q4 2025n = 340 contracts
Clauses detected

+31%

vs historical manual review

Q4 2025calibrated with 200 contracts
Cost per review

−61%

internalized by hour

Q4 2025n = 340 contracts

─ Deliverables

  • Internal portal with firm SSO
  • AI pipeline with 14 configurable categories
  • Reports with exact citations and page numbers
  • Integration with existing document management system
  • Audit panel: what was processed, when, by whom

─ Stack

Frontend
  • Next.js 15
  • Auth.js + SSO
  • shadcn/ui
AI
  • Claude Sonnet 4.6
  • Structured Outputs
  • pgvector
Orchestration
  • Inngest
  • Postgres
  • Cloudflare R2

─ Timeline

12 weeks · included calibration with 200 historical contracts

Testimonial ─ Client

I used to spend the morning reading. Now I spend the morning deciding. That's the difference between associate and partner.

Senior associate · Corporate firm MX

Does your case look like this?

If your operation looks like this, there's a system.

AI document review pipeline · CS-03 · MAVENOR