Normalized claim
Quantified impact: 40% decrease
Reduced call escalation by up to 40%.
ASAPP GenerativeAgent platform uses Amazon Bedrock to automate enterprise customer interactions
Use case typeCustomer service automationUpdated Jun 13, 2026
ASAPP’s AI-native customer service platform uses Amazon Bedrock to streamline service and safeguard data at enterprise-grade speed and accuracy. ASAPP built its GenerativeAgent Platform to orchestrate multiple large language models for voice and digital conversations end to end, with built-in privacy and security controls to protect customer data and improve service quality at scale.
- Organization
- ASAPP
- Industry
- Professional Services
- Location
- United States
- Published
- May 2026
Reported outcomes
Automation: +49%
Automation & deflection
Impact: Up to 40% lowerCost: −77%
Catalog median for automation & deflection deployments: +49% across 19 reported metrics. Compare benchmarks →
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Quantified impact: 90% increase
Automated more than 90% of contact center interactions.
Normalized claim
Quantified impact: 49% increase
Increased customer self-service engagements by 49%.
Normalized claim
Cost: 77% decrease
Reduced cost per chat by 77%.
Normalized claim
Quantified impact: 91%
Reported 91% first-call resolution for complex service issues.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- ASAPP
- Provider
- AWS
- Maturity
- Scaled Production
- Linked source
- AWS Solutions Case Study
ASAPP built its GenerativeAgent Platform to orchestrate multiple large language models for voice and digital conversations end to end, with built-in privacy and security controls to protect customer data and improve service quality at scale
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 3
- 1Customer Service Automation
- 2Conversational AI
- 3Contact Center Transformation
- ASAPP uses Amazon Bedrock, including Anthropic Claude models in Amazon Bedrock, to power its GenerativeAgent Platform.
- The platform orchestrates five to seven LLMs depending on use case, latency needs, and whether the interaction is voice or chat.
- ASAPP uses Amazon Bedrock Prompt Management to test prompts without deployment and explores Amazon Nova Sonic for real-time voice conversations.
- AWS built-in privacy and security controls allowed ASAPP to eliminate its homegrown PII redaction layer and improve response quality and speed.
- Reduced call escalation by up to 40%.
- Reduced cost per chat by 77%.
Architecture
ASAPP’s GenerativeAgent Platform orchestrates multiple LLMs for voice and digital customer conversations. It uses Amazon Bedrock to access foundation models, Amazon Bedrock Prompt Management to test prompts, and AWS region auto-selection for inference to maximize throughput and availability. AWS security controls replace a homegrown PII redaction layer, and the company is testing Amazon Nova Sonic for speech-to-speech experiences.
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 13, 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.