Procedural Simulation, AI creativity and stochastic modeling. Using Azure Cosmos DB to make games.
summary
A procedurally generated universe of planets, populations and AI landscapes is built end-to-end using Cosmos DB Gremlin graph as the real-time data layer, BabylonJS for web rendering, OpenAI for on‑the‑fly narratives and images, and Azure Event Hubs + event-driven Azure Functions to run stochastic simulation asynchronously. Small Ajax requests fetch node subgraphs, assets live in blob storage by ID, Jupyter notebooks validate models, and the system scales to many concurrent simulated worlds without blocking user experience.
AI-written summary · about
chapters (8)
- 0:00Procedural simulation & AI
- 1:11Cosmos DB for real-time sim
- 3:59Understanding stochastic modeling in depth
- 5:26AI for game narratives
- 7:14Infrastructure & microservices
- 9:43Async AI processing
- 11:09Event-driven stochastic modeling
- 13:14Industrial apps & closing
related talks
18mAccelerating 3D simulation workflows with NVIDIA Omniverse and DGX Cloud on Azure
48mGaming Industry use cases for Azure & AI
46mSupercharging game dev with Microsoft's cloud native and AI technology
50mBuilding AI ready applications
28mAccelerating Real-Time Analytics with Cosmos DB and GPU-Enhanced Serverless Apache Spark
46mMultimodel Multimodal and Multiagent innovation with Azure AI
36mApplied AI with Eclipse Graphene
46mMind your NPCs and Q’s: what’s next for Game AI?