Zuva: IDP Software Vendor

4 min read

On This Page

AI-powered contract analysis platform spun out from Kira Systems, specializing in document processing APIs and corporate legal workflows.

Overview

Zuva emerged from Kira Systems following Litera's acquisition in 2021, retaining 34 employees and over 10 years of machine learning technology. The company closed a $20 million CAD Series A led by Insight Partners at launch, building its DocAI platform on Kira's core ML stack - over 1,200 pre-trained models covering 36+ business agreement types.

The company operates under a structural constraint that shapes its entire go-to-market: under the terms of the Kira-Litera deal, Zuva is restricted to selling only to corporate legal departments - law firms are contractually excluded. That restriction sharpens focus but caps the addressable market. Within it, Zuva serves two distinct channels: developers and technical teams through API licensing, and in-house legal teams directly through Zuva Analyze, its first end-user product launched in September 2024.

Microsoft is a named API customer, using Zuva's technology to automate legal approval workflows for third-party software licensing requests - a distribution channel distinct from the direct-to-legal-team product Zuva is building alongside it.

How Zuva Processes Documents

Zuva's processing pipeline begins with OCR using the Kofax Omnipage engine with ML post-processing, converting 60+ document and image formats into plain text, images, or Protobuf layout files. From there, 1,200+ pre-trained AI models handle document classification and clause extraction across 36+ business agreement types - a model library inherited from Kira's decade of legal ML development.

The platform exposes this capability through RESTful APIs and a Python SDK, with Power Automate connectors for no-code integration. Deployment runs either cloud-hosted or on-premise via Kubernetes. Documents are retained for 7-14 days before automatic expiration. Continuous learning algorithms refine model accuracy over time through usage patterns, and real-time collaboration supports simultaneous multi-user access with version control.

For end users, Zuva Analyze surfaces this pipeline as a direct contract review application. Beta users reported reviewing contracts 2-3x faster than manual processes - a figure from Zuva's own testing with no independent benchmark cited. A free trial is available at zuva.ai without a sales call.

Use Cases

Zuva Analyze targets in-house legal departments handling their own deal review without routing work to outside counsel. As CEO Noah Waisberg explains: "Being able to go faster for a corporate is pretty attractive, especially if it's a corporate who's thinking about doing some of their own deals so they don't have to send stuff over to a law firm." The 2-3x speed claim applies to contract review tasks including clause extraction and agreement classification across the 36+ supported agreement types.

Pricing offers both subscription and per-project options. The per-project model is uncommon among contract review competitors and targets legal teams with variable rather than continuous workloads. Teams evaluating legal document automation workflows will find Zuva's corporate-only focus a meaningful differentiator from platforms that serve both law firms and in-house departments. Recital, which also specializes in contract lifecycle management for legal teams, offers a comparable point of comparison for in-house departments weighing dedicated contract intelligence tools.

Developer Integration

Before Zuva Analyze, Zuva operated exclusively as an API business - licensing its ML models to software companies and technical consultants building document processing applications. Waisberg positioned this explicitly at launch: "Customers will be other software companies or technical consultants that are building applications." Microsoft's use of the API for internal legal approval workflows illustrates the enterprise procurement channel this model reaches - distinct from, and running in parallel with, the direct Zuva Analyze product.

Integration options include RESTful APIs, a Python SDK, and Power Automate connectors. Developers building extraction pipelines on open-source tooling may also evaluate Unstract, which offers a no-code LLM platform with hallucination mitigation for similar structured extraction tasks. See the Zuva API documentation for file submission details and the OCR documentation for OCR service specifics.

Enterprise Contract Analysis

For organizations processing high volumes of business agreements - NDAs, MSAs, licensing contracts, and similar documents - Zuva's 1,200+ pre-trained models provide clause extraction and classification without custom training. The Kofax Omnipage OCR engine handles degraded or scanned source documents. Cloud or on-premise Kubernetes deployment accommodates data residency requirements common in regulated enterprise environments. Teams requiring structured extraction from financial or legal documents with source grounding may also consider LangExtract, Google's open-source Python library built for precisely that use case. Organizations with broader contract intelligence needs spanning procurement and vendor management may find Evolution AI, which serves NatWest and Deutsche Bank on complex financial and legal document processing, a relevant alternative to evaluate alongside Zuva.

Technical Specifications

Feature Specification
Supported Formats 60+ document and image formats (PDF, DOC, DOCX, TXT)
OCR Engine Kofax Omnipage with ML post-processing
Output Formats Plain text, images, Protobuf layout files
Integration RESTful APIs, Python SDK, Power Automate connectors
Deployment Cloud-based or on-premise Kubernetes
Document Retention Automatic expiration (7-14 days)
AI Models 1,200+ pre-trained models for 36+ business agreement types
Pricing Subscription and per-project options
End-User Product Zuva Analyze (GA as of September 2024)
Market Restriction Corporate legal departments only; law firms excluded by contract

Resources

Company Information

Website: https://zuva.ai/ Founded: 2021 Employees: 34 Location: Toronto, Canada Parent: Independent (spun out from Kira Systems following Litera acquisition)