How MoEngage built agentic customer engagement on Amazon Bedrock AgentCore
MoEngage built Merlin AI, a set of AI agents on Amazon Bedrock and Amazon Bedrock AgentCore that let marketing and product teams draft, analyze, and adjust campaigns from a single conversation. Learn how MoEngage turned its existing APIs into MCP tools and kept each tenant's data isolated while giving agents secure access to live platform data.
First seen by Oriel on .
AI summary
This AWS case study explains how MoEngage used Amazon Bedrock, AgentCore runtime, and MCP to make its customer-engagement platform agentic while preserving tenant isolation and user control.
- Merlin AI provides embedded, conversational, custom, and decisioning agents for campaign creation, analytics, segmentation, content, flows, and individualized channel decisions.
- MoEngage generated MCP tools from existing OpenAPI 3.0 specifications with FastMCP, keeping tool definitions synchronized as APIs change.
- JWT validation, forwarded tenant context outside tool arguments, isolated sessions, Guardrails, and backend validation protect identity, data, responses, and execution.
- Glance reached campaign go-live 50% faster, achieved a 38% push click-through uplift, and produced about three times more content variants per campaign.
- MoEngage reports 60–70% less manual effort, 20–30% higher conversion from goal-based decisioning, and over 50% lower AI infrastructure costs than self-hosted models.
#amazon bedrock #agentcore #mcp #customer engagement
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| AWS Machine Learning Blog | 2915fd77bac534686e62cc7588876a9c0f53a15a | https://aws.amazon.com/blogs/machine-learning/how-moengage-built-agentic-customer-engagement-on-amazon-bedrock-agentcore/ Read discussion |