What challenges did Unifi face before AI implementation?

The legal team manually processed collective bargaining agreements and other contracts, consuming hundreds of hours per year. Earlier AI attempts did not produce sufficiently accurate or consistent results for long, complex documents with specialized terminology. The team needed natural-language search and faster access to clause-level information across contracts up to 200 pages and 50 MB.

What was the impact of the AI solution?

Contract processing time was reduced from days to minutes. The solution enabled accurate natural-language search over large contracts and improved the legal team’s responsiveness. Unifi reported performance comparable to legal products costing about 30 times more. The low-code implementation went live in less than two months.

Source

MicrosoftEvidence: Medium50/100

Unifi reduced contract processing from days to minutes using Copilot Studio and Power Platform

Use case typeLegal document automationUpdated Jun 13, 2026

Unifi, North America’s largest provider of aviation ground handling services, needed to reduce the manual effort its legal team spent processing and reviewing collective bargaining agreements and other large contract documents. The company had struggled to achieve consistent extraction and search quality with earlier AI approaches because the documents were long, unstructured, and filled with specialized legal and industry terminology. Using Copilot Studio, Power Platform, SharePoint, Dataverse, Power Automate, AI Builder, and Power BI, Unifi built a low-code contract management solution that automatically extracts contract text, identifies key clauses, generates summaries, structures metadata, and makes the content searchable for legal teams.

Organization: Unifi
Industry: Logistics
Location: United States
Published: May 2026

Reported outcomes

30x

timeTime & speed

Strategic outcomes

Speed & agilityReduced contract processing time dramaticallyNew product / capabilityEnabled natural-language contract searchBetter decisions & insightImproved access to clause-level informationCompetitive differentiationDelivered legal-product-level performance

Catalog median for time & speed deployments: +60% across 143 reported metrics. Compare benchmarks →

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Time: 30 x increase

Microsoft Customer StoriesMay 13, 2026Customer storyInferred claimMedium evidence strength

Unifi reported performance comparable to legal products costing about 30 times more.

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: Unifi
Provider: Microsoft
Maturity: Unknown
Linked source: Microsoft Customer Stories

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 3 of 5

1Document processing automation
2Contract analytics
3Natural language search

The legal team manually processed collective bargaining agreements and other contracts, consuming hundreds of hours per year.
Earlier AI attempts did not produce sufficiently accurate or consistent results for long, complex documents with specialized terminology.
The team needed natural-language search and faster access to clause-level information across contracts up to 200 pages and 50 MB.

Unifi created a multi-stage AI-driven workflow with Power Automate triggering extraction and classification steps when a contract is uploaded to SharePoint.
AI Builder text recognition was used to extract text from scanned PDF images, while Power Automate prompts helped refine deterministic attributes and formatting.
Extracted content was stored in Dataverse, separated into raw text and metadata tables to improve retrieval quality, and exposed through an agent built in Copilot Studio and run in Microsoft 365 Copilot.
Managers also used Power BI dashboards for high-level visibility into contract activity and status.

Technologies

Copilot Studio Power Platform Power Automate AI Builder Dataverse SharePoint Power BI Microsoft 365 Copilot

Contract processing time was reduced from days to minutes.
The solution enabled accurate natural-language search over large contracts and improved the legal team’s responsiveness.
Unifi reported performance comparable to legal products costing about 30 times more.
The low-code implementation went live in less than two months.

Architecture

A contract uploaded to SharePoint triggers Power Automate flows. AI Builder OCR/text recognition extracts text from scanned contract pages; prompts in Power Automate add deterministic fields and formatting; key clauses and summaries are written into Dataverse tables that separate raw text from metadata; a custom agent in Microsoft 365 Copilot consults the Dataverse knowledge repository for natural-language search and query insights; Power BI provides dashboard reporting.

Sources & evidence1

Evidence: Medium50/100Evidence strength