Normalized claim
Time: 7 hours decrease
Reduced root cause analysis time from ~7 hours to less than 10 minutes per issue.
How Apollo Tyres is Unlocking Machine Insights Using Agentic AI-Powered Manufacturing Reasoner
Use case typePredictive maintenanceUpdated Jun 13, 2026
Apollo Tyres Ltd, a leading tire manufacturer, faced a challenge in accelerating root cause analysis (RCA) and reducing dry cycle time (DCT) of automated curing presses to improve operational efficiency. They developed Manufacturing Reasoner, a generative AI multi-agent system powered by Amazon Bedrock Agents that integrates real-time industrial IoT data for automated RCA and natural language insights. The solution uses multistep AI agents for reasoning, explanation generation with Anthropic Claude models, visualization with dynamic charts, and Amazon Bedrock Guardrails for secure and accurate AI output. This implementation reduced RCA time from about 7 hours to less than 10 minutes per issue, an 88% reduction in effort, improved real-time anomaly detection, and enabled preventive action. The targeted savings are estimated at 15 million INR per year in the passenger car radial division across three plants.
- Organization
- Apollo Tyres Ltd
- Industry
- Manufacturing
- Location
- India
- Published
- June 2025
Reported outcomes
10 minutes
timeTime & speed
7 hourstime−88%quantified impact
Strategic outcomes
Speed & agilityAccelerated root cause analysisCost efficiencyReduced manual RCA effortRisk & complianceEnabled preventive maintenance actionsBetter decisions & insightImproved real-time anomaly detection
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Time: 10 minutes decrease
Reduced root cause analysis time from ~7 hours to less than 10 minutes per issue.
Normalized claim
Quantified impact: 88% decrease
Achieved 88% reduction in manual effort for RCA.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Apollo Tyres Ltd
- Provider
- AWS
- Maturity
- Production
- Linked source
- AWS Machine Learning Blog
Apollo Tyres Ltd, a leading tire manufacturer, faced a challenge in accelerating root cause analysis (RCA) and reducing dry cycle time (DCT) of automated curing presses to improve operational efficiency
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 3
- 1Root Cause Analysis
- 2Predictive Maintenance
- 3Process Optimization
- Manual root cause analysis for curing presses was slow (around 7 hours per issue) and needed experts from multiple departments.
- Existing tools could not perform detailed subelement-level diagnostic analysis.
- Insights were not real-time causing delayed corrective actions.
- Developed Manufacturing Reasoner using Amazon Bedrock Agents to perform natural language multistep queries on real-time IoT data.
- The system uses multiple AI agents for classification, transformation, explanation, and visualization.
- It integrates AWS services including Amazon EC2, Amazon OpenSearch Service, Amazon Redshift, and Anthropic Claude models.
- Amazon Bedrock Guardrails ensure secure, compliant, and relevant AI outputs.
- Reduced root cause analysis time from ~7 hours to less than 10 minutes per issue.
- Achieved 88% reduction in manual effort for RCA.
- Enabled earlier detection and preventive maintenance actions.
- Estimated annual savings of 15 million INR in one division within three plants.
Architecture
Architecture leverages Amazon Bedrock Agents with multi-agent workflow including transformation engine agent, explainer agent (using Anthropic Claude Haiku), visualization agent (Anthropic Claude Sonnet), and AWS services such as Amazon EC2, Amazon OpenSearch Service, and Amazon Redshift, with Amazon Bedrock Guardrails for security.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Quantified outcome available
- Technical implementation details available
Type: Blog PostPublished: Jun 16, 2025Publisher: AWS Machine Learning BlogEvidence: VendorConfidence: Medium
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
Loading comments...