Normalized claim
User satisfaction: 11% increase
improved user satisfaction by 11%
Siemens: Agentic generative AI global search with Amazon Bedrock and Amazon Nova
Use case typeLegal AI assistantUpdated Jun 13, 2026
Siemens used Amazon Bedrock and Amazon Nova Foundation Models to streamline complex global search across 15-20 Siemens sites. Customers can enter natural-language queries and receive relevant information in seconds, instead of sifting through marketing pages to find technical documentation. An AWS Lambda function orchestrates validation, classification, summarization, and guardrail agents for the search workflow.
- Organization
- Siemens
- Industry
- Tech & Comms
- Location
- Germany
- Published
- May 2026
Reported outcomes
+300%
search speedTime & speed
+11%user satisfaction−70%costs
Strategic outcomes
Customer experience & trustEliminated no-results searchesCustomer experience & trustImproved user satisfactionSpeed & agilityLaunched in under one yearRisk & complianceEstablished legal AI risk governance framework
Catalog median for time & speed deployments: +60% across 143 reported metrics. Compare benchmarks →
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Search speed: 300% increase
improved search speed by 300%
Normalized claim
Costs: 70% decrease
reduced costs by 70% compared with the models that Siemens was using before
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Siemens
- Provider
- AWS
- Maturity
- Production
- Linked source
- AWS Solutions Case Study
Search complexity caused no-results searches, slow performance, frustration, and operational cost
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 3
- 1Enterprise Search
- 2Agentic AI
- 3Knowledge Management
- Customers struggled to find technical documentation across 15-20 Siemens sites.
- Search users had to sift through marketing content to find technical specifications.
- Search complexity caused no-results searches, slow performance, frustration, and operational cost.
- Siemens implemented an AI-powered global search on AWS.
- Amazon Bedrock and Amazon Nova Foundation Models provide the generative AI capability.
- AWS Lambda orchestrates the end-to-end search flow and the AI agents.
- Validation agents check whether a query can be answered from a knowledge base.
- Classification agents route intent to the correct backend or knowledge base.
- Summarizer agents condense results.
- Guardrail agents filter disallowed topics, non-Siemens products, and risky legal prompts.
- The solution launched in less than one year from concept to deployment.
- It eliminated no-results searches.
- It improved user satisfaction by 11%.
- It improved search speed by 300%.
- It reduced costs by 70% compared with Siemens' previous models.
- The guardrail implementation contributed to a company-wide legal framework for generative AI risk governance.
Architecture
A natural-language search experience is backed by an AWS Lambda-orchestrated multi-agent workflow. Queries are validated, classified, searched against the appropriate knowledge base, summarized, and filtered by guardrail agents. Amazon Bedrock hosts the generative AI models, including Amazon Nova Foundation Models, for agent tasks and output generation.
Sources & evidence1
Evidence: Medium65/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: May 27, 2026Publisher: AWSEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
AI patterns
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.