Normalized claim
Cost: 50% decrease
AWS helped Oriserve reduce cost to serve by 50 percent versus other providers.
Oriserve generative AI voice/chat agents on AWS using Amazon Bedrock (India)
Use case typeCustomer service automationUpdated Jun 13, 2026
Oriserve is an India-based startup that builds enterprise-grade generative AI agents and conversation analytics for voice, chat, and email customer engagement across more than 120 languages and regional dialects. The company chose AWS to support rapid go-to-market, compliance needs, and scalable delivery of multilingual conversational AI applications.
- Organization
- Oriserve
- Industry
- Professional Services
- Location
- India
- Published
- May 2026
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Accuracy: 90%
Its voice bot reached 90 percent accuracy and 60 percent fewer word errors than industry standards.
Normalized claim
Accuracy: 60%
Its voice bot reached 90 percent accuracy and 60 percent fewer word errors than industry standards.
Normalized claim
Quantified impact: 75% increase
Vi, a named customer of Oriserve's solution, reportedly increased customer retention by 75 percent.
Normalized claim
Quantified impact: 50% increase
Oriserve reported 50 percent annual growth.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Oriserve, Vi
- Provider
- AWS
- Maturity
- Production
- Linked source
- AWS Customer Stories
It deployed applications on Amazon EC2 Auto Scaling and used Amazon EKS to manage Kubernetes-based microservices
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 4
- 1Customer Service Automation
- 2Conversational AI
- 3Speech Recognition
- Oriserve used Amazon Bedrock to build text and email bots on large language models including Anthropic Claude 3.5 and Meta Llama 3-70B, plus text embeddings.
- It deployed applications on Amazon EC2 Auto Scaling and used Amazon EKS to manage Kubernetes-based microservices.
- Oriserve also developed custom voice models for automatic speech recognition and used Bedrock to experiment with different language models more quickly.
Amazon Bedrock reduced LLM fine-tuning time from weeks to days.
Architecture
AWS-hosted microservices for generative AI agents and conversation analytics using Amazon Bedrock for model access, Amazon EC2 Auto Scaling for elastic compute, and Amazon EKS for container orchestration. The solution also includes custom voice models for ASR and uses managed ML experimentation to compare and fine-tune multiple LLMs.
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
Market context
AI patterns
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.