Toyota Revolutionizes Vehicle Design Process with Multi-Agent AI
Toyota Motor Corporation has launched an advanced multi-agent AI system—O-Beya—to accelerate the design and development of new vehicles. Facing engineering complexity and the challenge of knowledge retention as experienced experts retire, Toyota deployed O-Beya across its design teams. Using Azure OpenAI (GPT-4o), Azure Cosmos DB, Azure Durable Functions, and Azure AI Search, engineers receive automated support in specialized domains such as battery, motor, regulations, and systems control. Each AI agent utilizes Toyota's internal design data via Retrieval-Augmented Generation (RAG), ensuring precise, context-rich answers to technical queries and facilitating knowledge sharing. The solution's architecture leverages parallel processing with Azure Durable Functions for high performance and easy scaling as new agents are added. O-Beya currently supports 800 users, reducing information search times and supporting team collaboration. Plans are in place to further expand the system to additional domains and agents, ensuring ongoing innovation and operational efficiency.
- Organization
- Toyota
- Industry
- Automotive
- Location
- Japan
- Published
- November 2024
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Toyota
- Provider
- Microsoft
- Maturity
- Production
- Linked source
- Microsoft DevBlogs
Facing engineering complexity and the challenge of knowledge retention as experienced experts retire, Toyota deployed O-Beya across its design teams
Primary read
Use case focus
Showing 3 of 3
- 1Multi-Agent Generative AI for Automotive Design Support
- 2Retrieval-Augmented Generation for Technical Knowledge Management
- 3Automated Expert Assistance for Vehicle Engineering
- Developed 'O-Beya', a multi-agent generative AI system leveraging Azure OpenAI (GPT-4o) for specialized knowledge tasks.
- Employed Azure Cosmos DB for scalable, schema-less storage of conversations and to enable rapid vector search.
- Utilized Azure Durable Functions for orchestrating multiple AI agents in parallel with advanced workflow management.
- Applied Retrieval-Augmented Generation (RAG) using Azure AI Search and internal design data.
- Enabled permission-based access control and easy addition or refinement of agents for new technical domains.
- System adopted by 800 Toyota engineers for design and engineering support.
- Over 100 requests processed per month with positive user feedback.
Architecture
Toyota's 'O-Beya' multi-agent AI system uses Azure Durable Functions to orchestrate parallel execution of four specialized AI agents (battery, motor, regulations, system control). Each agent leverages a tailored Retrieval-Augmented Generation pattern utilizing Azure OpenAI Service for generative models, Azure Cosmos DB for scalable storage and vector search, and Azure AI Search for document retrieval. User queries trigger Durable Functions to activate all agents, with results compiled by generative AI. Cosmos DB stores conversational logs, supporting session context and permission-based access. The fan-out/fan-in model enables easy addition of new agents.
Sources & evidence1
- Customer explicitly identified
- Deployment status explicitly supported
- Technical implementation details available
- Recent evidence check available
- Last evidence check: Jun 1, 2026.
The same organization appears in newer AI deployment evidence.
- Same organization re-documented as recently as 2026.
- Cited source last checked Jun 1, 2026 — ok (0/1 broken).
Measures whether this deployment's public evidence persists — not whether the system is still in production.
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.