Microsoft Media and Entertainment United States

Unity

Enterprise Knowledge Search · IT Operations Automation

Documentation alone can’t always diagnose the problem. We have a vast amount of information and a vast number of subject matter experts who share their experience on our community forums,” explains Martina Johannesson, Senior Technical Product Manager (AI & Machine Learning) at Unity.

And when it comes time for users to interact with it, you can trust it will run smoothly without interruption.” The team ultimately used both GPT-4 and GPT-3.5 Turbo models as the foundation for Muse Chat, striking a bal
The functionality of Muse Chat also helps set Unity apart, as it’s one of the only 3D content creation engines which has a built-in large language model that can access the details of users’ projects.

Reported impact

Business outcome

Although Muse Chat is still early in its rollout, Unity believes it is a major opportunity for game developers to solve problems in new ways. Game development can be a complex art form, and many creators may not want to spend hours refining component setups in their games and rather spend their time elsewhere,” says Johannesson. They’re more interested in the overall game flow and experience.

  • Cost Reduction
  • Customer Experience
  • Productivity Improvement
  • Scalability

Solution

Unity built this solution on Azure OpenAI Service. Documentation alone can’t always diagnose the problem. Azure OpenAI Service provides the generative AI model layer used for summarization, drafting, classification, or copilots in the workflow. Unity provides a platform for 3D games, apps, and experiences, but the sheer volume of documentation can make learning the engine challenging. The company used Microsoft Azure OpenAI Service to build Muse Chat, an AI assistant that can guide creators through common questions and help troubleshoot issues to make game development easier. Business results include although Muse Chat is still early in its rollout, Unity believes it is a major opportunity for game developers to solve problems in new ways. Game development can be a complex art form, and many creators may not want to spend hours refining component setups in their games and rather spend their time elsewhere,” says Johannesson.

Solution architecture

1 components · 1 layer
  1. Compute
    • Azure OpenAI Service Provides the generative AI model layer used for summarization, drafting, classification, or copilots in the workflow.

Architecture clues

  • The implementation relies on Azure OpenAI Service as a core technical building block.

Evidence from the source

Although Muse Chat is still early in its rollout, Unity believes it is a major opportunity for game developers to solve problems in new ways.
And when it comes time for users to interact with it, you can trust it will run smoothly without interruption.” The team ultimately used both GPT-4 and GPT-3.5 Turbo models as the foundation for Muse Chat, striking a bal
Documentation alone can’t always diagnose the problem.
The functionality of Muse Chat also helps set Unity apart, as it’s one of the only 3D content creation engines which has a built-in large language model that can access the details of users’ projects.
Unity provides a platform for 3D games, apps, and experiences, but the sheer volume of documentation can make learning the engine challenging.
Transparency Evidence & methodology 55/100 reference value · 85% confidence · 1 source

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

01

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 value55/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth15/25
    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 impact0/25
    0 metrics describe measurable impact.
  • Deployment scale0/10
    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 traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity6/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

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

  1. Microsoft

    Unity customer story

    First-party
    https://www.microsoft.com/en/customers/story/1769469533256482338-unity-technologies-azure-open-ai-service-gaming-en-united-states
    Source type
    Vendor-published customer story
    Published
    May 21, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page May 21, 2024 · Microsoft · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.