EY Commercial and Professional Services global

EY

Enterprise Knowledge Search

EY wanted enterprise-scale generative AI that employees could use in a private, secure environment, but off-the-shelf tools lacked EY-specific context and raised data privacy, information security, governance and executive alignment concerns that could stall adoption.

Read the original story Explore all use cases

81% adoption rate

launched to 300,000 EY people

more than 116 million prompts processed to date

proof of concept (POC) in approximately four weeks

Reported impact

Business outcome

EY established a secure enterprise GenAI platform with broad adoption, faster internal knowledge access, shared collaboration patterns and a reusable foundation for new agents and copilots, helping the firm operate more like an AI-first organization without compromising governance or brand safety.

Solution

EY chose to build EY.ai EYQ as a custom generative AI ecosystem instead of buying consumer-grade tools. The platform was developed in quick phases and is powered by EY Fabric, whose reusable cloud, data, intelligence, development and experience components gave teams a scalable foundation. EYQ began with a secure ChatGPT-like experience, then expanded into domain-specific conversational agents that answer questions in areas such as HR and client delivery using EY knowledge and data. A robust orchestration framework decides which agents, or which combination of agents, should respond based on user context, while prompt management lets users improve and share prompts through a centralized library. Shared workspaces make EYQ a multiuser collaborator, and developer environments let technologists publish new copilots from Microsoft Copilot Studio into the ecosystem. Microsoft Azure and Azure OpenAI service provide the core infrastructure for one of EY's largest private GenAI environments.

Data flow

EY knowledge, data and domain context are routed through EY Fabric into EYQ's private Azure and Azure OpenAI environment. The orchestration framework selects the relevant conversational agents, prompt management improves user inputs, shared workspaces support team collaboration, and new copilots built in Copilot Studio can be published back into the ecosystem.

Solution architecture

8 components · 3 layers

Compute
- Microsoft Azure Hosts the private enterprise infrastructure that runs EYQ at global scale.
- Azure OpenAI service Provides the core LLM capabilities behind EYQ's conversational experiences.
Serving
- EY.ai EYQ Provides the secure employee-facing GenAI experience and hosts the broader internal AI ecosystem.
- domain-specific conversational agents Answer specialized questions using context from HR, delivery and other internal domains.
- shared workspaces Let multiple EY users collaborate with EYQ inside a shared conversation and work context.
- Microsoft Copilot Studio Enables teams to build new copilots that can be published into EYQ's ecosystem.
Orchestration
- EY Fabric Supplies the reusable cloud, data, intelligence and development foundation for rapid enterprise scaling.
- orchestration framework Selects and coordinates the best agent or agent combination for each user request.

Architecture clues

An orchestration framework can invoke multiple agents in a single conversation based on user context.
Domain-specific agents were added after the initial ChatGPT-like deployment to infuse EY-specific knowledge and data.
EYQ is powered by EY Fabric and built on Microsoft Azure and its OpenAI service.
Shared workspaces and Copilot Studio publication flows extend EYQ from single-user chat into a broader collaboration and development platform.

Evidence from the source

"Built on Microsoft Azure and its OpenAI service, EYQ is one of the largest private, secure GenAI enterprise ecosystems globally."

"EYQ is powered by EY Fabric, a global foundational technology platform."

"The POC was successfully launched to 300,000 EY people, providing them with a secure, private environment to experience the capabilities of GenAI."

"The impressive user adoption rate of EY.ai EYQ has surpassed 81% across the EY organization, with more than 116 million prompts processed to date."

"This framework intelligently manages the integration and interaction of related domain-specific agents based on user-provided context."

Transparency Evidence & methodology 90/100 reference value · 85% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value90/100

Problem clarity20/20
Measures whether the customer's operational problem is specific enough to compare.
Implementation depth25/25
Rewards named components, data flow, integrations, and architecture detail.
Outcome specificity20/20
Measures whether the reported benefit is concrete rather than a generic claim.
Quantified impact15/25
1 metric describe measurable impact.
Deployment scale10/10
Rewards evidence of a live or scaled deployment and meaningful integration scope.

Evidence confidence85%

Source authority20/25
The main evidence is an official vendor-published customer story.
Claim traceability25/25
12 of 12 key fields link to a named source.
Direct evidence20/20
5 direct source quotes retained.
Date provenance0/10
The publication date has no documented provenance.
Source transparency10/10
1 source reference document publisher, URL, authority, retrieval, and supported fields.
Implementation specificity10/10
Rewards source-backed components, data flow, quantified impact, and a specific outcome.

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

EY
Case study: EY realizes GenAI leap with EYQ | EY - Global

First-party
https://www.ey.com/en_gl/insights/ai/how-ey-is-unlocking-the-next-iteration-of-genai-advancement-with-eyq

Source type
Vendor-published customer story
Supports
- Customer
- Industry
- Region
- Company size
- Business problem
- Solution
- Products
- Solution components
- Data flow
- Integrations
- Business outcome
- Metrics
- Architecture
- evidence quotes

Date evidence

First archived Apr 24, 2025 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
Open date source

Similar use cases

See all like this

Google Cloud Modified · Oct 9, 2026 Rentokil Initial Commercial and Professional Services United Kingdom Rentokil Initial manages a dynamic workforce of over 65,000 colleagues worldwide. While the company has built its collaborative foundation on Google Workspace since 2008, leadership recognised a vital opportunity to… Rentokil Initial supports 30,000 active daily Gemini users across the global organization Developed a bespoke,… Enterprise Knowledge Search Cloud Run · Firebase · Gemini Live

OpenAI Oct 8, 2026 Cooley Commercial and Professional Services North America Capital markets involve huge amounts of information that need to be synthesized and analyzed. "For our lawyers, it’s always very busy," explains David Wang, Chief Innovation Officer at Cooley. Cooley is an international law firm with a reputation for helping companies navigate capital markets and… Document ProcessingEnterprise Knowledge Search ChatGPT Work · GO Public

OpenAI Oct 8, 2026 Gilbert + Tobin Commercial and Professional Services Asia-Pacific & Oceania Gilbert + Tobin needed to improve research, drafting, analysis, and operational workflows across a law firm without compromising client confidentiality, governance requirements, or human accountability. 87% active usage among enabled ChatGPT users Document ProcessingEnterprise Knowledge Search ChatGPT Enterprise · ChatGPT Work · Codex