Skip to content
Primores AI wiki

AI Legal Case Studies: Contract Analysis, Compliance, Research

AI Legal Case Studies

TL;DR: 5 legal AI deployments. Altumatim achieves 90% automation in contract analysis. Inspira automates 80% of legal document processing. Contraktor reduced contract review time by 75%.

Why This Page Exists

Legal work is document-heavy and expensive. AI doesn’t replace lawyers - it handles the grunt work so lawyers can focus on judgment and strategy.

Altumatim

What they did: Altumatim, a legal tech startup, uses a platform powered by Gemini on Vertex AI to analyze millions of documents for eDiscovery. This accelerates the process from months to hours, improves accuracy to over 90%, and enables attorneys to focus on building compelling legal arguments.

Key metrics: 90%

Inspira

What they did: Inspira, a legal tech company, tackles the time-intensive challenge of legal document analysis by providing lawyers with an AI-powered solution built on Google Cloud. Leveraging Gemini, Vertex AI, and BigQuery, Inspira’s platform automates legal document search, analysis, and drafting to reduce workflow times by 80%, allowing lawyers to find answers and relevant decisions in minutes or hours instead of weeks.

Key metrics: 80%

Contraktor

What they did: Contraktor developed a project to analyze contracts with AI. As a result, the company achieved a reduction of up to 75% in the time taken to analyze and review a contract, with the possibility of both reading and extracting relevant data from the documents.

Key metrics: 75%

Guane

What they did: Guane, a Colombian AI company, uses Vertex AI with Gemini 1.0 and Document AI to power AURA for law firms, automating the analysis of land restitution sentences and embargo notices. The platform reduced land restitution sentence processing from 12 hours to 6 minutes and processes hundreds of thousands of embargo documents in minutes.

Key metrics: 12 hours

Guane

What they did: Guane also uses Vertex AI, Gemini, and Document AI to power AURA for law firms, automating the analysis of land restitution sentences and embargo notices. The platform reduced land restitution sentence processing from 12 hours to 6 minutes and processes hundreds of thousands of embargo documents in minutes.

Key metrics: 12 hours

Key Patterns

  1. Contract review scales. AI reviews hundreds of contracts for specific clauses.
  2. Due diligence accelerates. Document analysis in days instead of weeks.
  3. Compliance checking. AI flags potential issues for human review.
  4. Research synthesis. AI summarizes case law and precedents.

More Implementations (Without Specific Metrics)

These companies are using AI in this domain but without publicly quantified results yet. Included for completeness and SEO discoverability.

  • DocuSign: DocuSign is using Gemini to power new features that summarize complex agreements, identify key clauses, and help user…
  • Freshfields: Freshfields, a global law firm with over 280 years’ experience, uses Gemini to power Dynamic Due Diligence, its propr…
  • Harvey: Harvey, a legal AI company, uses Gemini 2.5 Pro on Vertex AI to automate complex document reviews, a major pain point…
  • Huge: Huge, an American business services agency, utilized Gemini Enterprise to create AI agents that automate market resea…
  • Jusbrasil: Jusbrasil uses Jus IA and Gemini to automate legal research and drafting in seconds, leveraging 1.2 billion documents…
  • Markups.ai: Markups.ai, an AI contract negotiation agent, turns a days-long human legal review into a minute(s) automated process…
  • Justicia Lab: Justicia Lab is developing an AI-powered assistant that will simplify legal processes for asylum seekers and immigran…
  • Quanscient: Quanscient, a Finnish cloud-based multiphysics simulation platform company, built an anomaly detection tool using Gem…
  • SuperSign: SuperSign’s platform facilitates digital contract signing processes with Gemini, as well as creating solutions focuse…
  • Vodafone: Vodafone uses Vertex AI to search and understand specific commercial terms and conditions across more than 10,000 con…

Sources