Bayer's New AI Cuts Crop Research Time by 80%
This could speed up development of better seeds and crops, affecting your food supply.
Bayer Crop Science built the Agentic Decision Engine (ADE), a multi-agent, natural language interface over its Connected Decision Engine (CDE), to close the gap where explaining a result meant piecing together context from APIs, documentation, metadata stores, dashboards, and logs. A supervisor agent routes each question to a specialist agent, the specialist retrieves context from the relevant system, and the user receives an answer without navigating the operational stack.
In its first phase, ADE resolves about 80 percent of user questions without an engineer in the loop. ADE runs on Amazon Bedrock AgentCore, and Bayer runs its own LangGraph-based orchestration on the framework-agnostic runtime. ADE runs 22 specialist agents in production, each scoped to one domain with its own tools and data sources.
- Bayer's new AI system answers 80% of questions about plant breeding data without engineers.
- It runs on Amazon Bedrock AgentCore, a service for building and managing AI agents.
- This speeds up research, potentially leading to better crops and a more stable food supply.
Why It Matters
Faster crop research could mean more resilient food supplies and potentially lower prices at the grocery store.