MicrosoftPilotEvidence: Medium55/100

EY rolls out agentic AI in assurance on Azure (EY Canvas)

EY launched enterprise-scale agentic AI in assurance, embedding a multi-agent framework into EY Canvas, its global assurance technology platform. The platform is integrated with Microsoft Azure, Microsoft Foundry, and Microsoft Fabric and supports audit workflows across EY’s global assurance network, which processes more than 1.4 trillion lines of journal entry data per year.

Organization
EY
Published
April 2026

Planned next steps

  • The capability will support 130,000 assurance professionals across 160,000 audit engagements in more than 150 countries and territories.
  • EY expects the system to support all end-to-end audit activities by 2028.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
Customer
EY
Provider
Microsoft
Maturity
Pilot

EY said the capabilities followed extensive testing and piloting before enterprise-scale rollout and are intended to support all end-to-end audit activities by 2028

Customer identity supportedSource describes one deploymentMaturity supported

Primary read

Use case focus

Showing 3 of 4

  • 1Agentic AI orchestration
  • 2Audit automation
  • 3Workflow automation
  • EY integrated a multi-agent framework into EY Canvas to orchestrate complex tasks, processes, and technologies across audit phases.
  • The deployment uses Microsoft Azure, Microsoft Foundry, and Microsoft Fabric as the cloud and AI foundation.
  • EY said the capabilities followed extensive testing and piloting before enterprise-scale rollout and are intended to support all end-to-end audit activities by 2028.
EY said the platform processes more than 1.4 trillion lines of journal entry data per year.
Architecture

A multi-agent framework is integrated into EY Canvas, EY’s global assurance technology platform, and connected with Microsoft Azure, Microsoft Foundry, and Microsoft Fabric to orchestrate audit workflows across a global enterprise-scale assurance operating model.

Sources & evidence1
Evidence: Medium55/100Evidence strength
  • Customer explicitly identified
  • Deployment status explicitly supported
  • Independent source available
  • Technical implementation details available
Type: News ArticlePublished: Apr 7, 2026Publisher: CPA Practice AdvisorEvidence: SecondaryConfidence: Low

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Was this useful?

Community

Comments

No published comments yet.