back_office_ops · education · workflow
UCLA OARC delivers near real-time generative AI image and 3D pipeline for immersive theater production Xanadu using AWS
UCLA's REMAP center needed AI microservices capable of handling at least 80 concurrent mobile phone users per performance with a mean round-trip time under 2 minutes, with no tolerance for graceful degradation during live theatrical performances.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Audience submits mobile sketch
Participants are asked to draw a sketch on their mobile phone for a specific task such as creating a background or placing muses in custom poses.
Tools used
Amazon SageMaker AIAmazon BedrockAWS LambdaAmazon SQSAmazon SNSAmazon DynamoDBAmazon EFSAmazon S3Amazon EC2 G6Amazon EventBridgeAmazon CloudWatchAWS CodeBuildHuggingFaceClaude 3.5 SonnetDeepSeek VLMNova CanvasStable Diffusion 3.5SDXLSPAR3DControlNetInstantIDFirebase · partnerPyTorchUnreal EngineGitHub
Outcome
OARC successfully delivered 7 live performances with about 500 total audience members co-creating media, achieving processing times of 40–60 seconds on g6.4xlarge instances and 20–30 seconds on g6.12xlarge instances.
Results
Time savedunder 2 minutes
Volume80 mobile phone users
Cost replacedabout 500
Running sinceMay 15, 2025
Grounding & classification
Source type: technical build writeup
53 fields verified against source quotes.
computer visioncontent generationmulti agent workflowform submissionhuman review describedmetric backednamed customerproduction runtime claimedtools describedvendor confirmedworkflow describededucationmediacycle time reductionthroughput increasetechnical build writeupback office opsagentic task executionextract classify route