Toyota Motor Corporation
O-Beya multi-agent system for powertrain engineers
Toyota gives about 800 powertrain engineers a system of nine AI agents
Problem
The number of items to develop is growing and senior powertrain experts are retiring, which risks losing their knowledge.
Approach
Toyota built O-Beya, a set of nine agents that store and share engineering expertise. It runs on Azure OpenAI Service with GPT-4o, Azure Functions and Azure Cosmos DB for vector search.
Results
Takeaway
Some 800 powertrain engineers have had access since January 2024. Microsoft reported hundreds of uses a month but did not quantify time savings.
Categories
- Size
- Large enterprise
- Industry
- Manufacturing
- Business function
- IT and R&DInternal work and knowledge management
- Innovation type
- Process innovation
- AI technology
- AI agentsGenerative AI
- Adoption
- Built in-house
- Evidence
- Vendor's case study
Sources
Source summaries
Microsoft described Toyota's O-Beya system of nine agents for powertrain engineers. About 800 engineers had access, and the system was used hundreds of times a month.
Full details are in the original sources.