Building an agent mesh in 3 days: Syngenta's Bedrock AgentCore journey
Swiss agriculture company Syngenta built a federated multi-account agent mesh using Amazon Bedrock AgentCore, deploying the initial architecture in 3 days and six cross-functional agents in 4 weeks, achieving 20% better latency and 40% faster deployment, with its Austyn data-analytics agent now used by up to 12,000 internal monthly active users.
Overview
Swiss agriculture company Syngenta built a federated multi-account agent mesh using Amazon Bedrock AgentCore, deploying the initial architecture in 3 days and six cross-functional agents in 4 weeks, achieving 20% better latency and 40% faster deployment, with its Austyn data-analytics agent now used by up to 12,000 internal monthly active users.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
As a large multinational with over 30,000 employees in more than 90 countries, Syngenta had many teams across functions and business units experimenting with AI independently, leading to duplicated agent-building effort that could not be easily reused because agents weren't built to a common technical standard or couldn't be found by other teams; Syngenta wanted company-wide, interoperable AI innovation with centralized governance, security, and reduced technical debt.
The solution
Syngenta used Amazon Bedrock AgentCore to build a federated multi-account hub-and-spoke agent mesh, developed during a 3-day AWS Experience-Based Acceleration engagement. The central hub account provides orchestration, observability, and gateway services via AgentCore Gateway, while spoke accounts connect using AgentCore Runtime, a secure serverless hosting environment for agents. The mesh uses Agent2Agent and AG-UI protocols for inter-agent communication and Model Context Protocol for data retrieval, with AWS IAM and AgentCore identity management securing agent identities, plus catalogs and registries so business units can discover and reuse agents other teams have built.
Reported business value
Syngenta's agent mesh was operational in 3 days during the AWS EBA; the supply chain and marketing business units are actively deploying agents, with marketing building six agents in 4 weeks. Using AgentCore Runtime, Syngenta achieves 20 percent better latency than physical servers and deployment takes around 40 percent less time. Austyn, a widely adopted data-analytics agent built during the EBA, is now used by up to 12,000 internal monthly active users to run exploratory data analysis, plot charts, and create visualizations.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other agriculture entries in the register.
UPL optimizes supply chain operations with demand forecasting on Databricks
Global agriculture company UPL unified internal and third-party data sources (SAP, Salesforce, IoT, weather) on the Databricks Data + AI Platform with Unity Catalog to build a demand forecasting model that reduces product spoilage and supports AI-driven crop management and pest control across 20 countries.
UPLDatabricks SQL · Delta Lake · Delta Sharing +2
AWS Partner Adastra Supports KWS in Generative AI Adoption Using Amazon Bedrock
KWS, a global seed producer, uses Amazon Bedrock and generative AI to boost research speed and efficiency, supported by Adastra, an AWS Partner. Access to Amazon Bedrock's large language models gives KWS flexibility to prototype and test generative AI use cases without the cost of setting up its own large IT infrastructure, according to Bjørn Øst Hansen, KWS's senior research lead for knowledge discovery.
KWSAmazon BedrockBayer uses generative AI and machine learning to speed crop breeding and agronomy
Bayer uses AI and data science across its agriculture business. Its precision breeding platform, combining machine learning and digital twin technology, has cut a breeding cycle from five to six years down to four months. Bayer trained a large language model called E.L.Y. on internal agronomy data to answer farm management questions, and uses AI models to guide planting density and irrigation decisions on its own seed-production fields, increasing field productivity by over 30%; it also offers AI-powered seed scripts and planting-density recommendations to growers through its FieldView digital farming platform, which manages more than 220 million acres in over 20 countries.
BayerDigital twin technology · E.L.Y. (large language model) · CropKey +2Was this helpful?
Your feedback helps us improve our use case database