LIVE
OpenAI Partners with Chilean Ministry to Advance Public Sector AI Ambience Healthcare Expands Clinical AI Suite for Hospital Operations AI Models Vulnerable to Manipulation in Simulated Warfare Scenarios, Research Shows AWS Highlights Enterprise Governance and AI Workspace Quick Ahead of re:Invent 2026 LoanPro Integrates Amazon Bedrock to Automate Loan Servicing Workflows Google Brings Wallet App to iOS Users Across the United States Microsoft Reveals Cause of Global Outlook Outage AWS Outlines Phased Roadmap for Responsible Agentic AI Governance Google updates Gemini settings to separate chat history from AI model training Uber Eats and Zipline launch autonomous drone food delivery in Houston OpenAI Partners with Chilean Ministry to Advance Public Sector AI Ambience Healthcare Expands Clinical AI Suite for Hospital Operations AI Models Vulnerable to Manipulation in Simulated Warfare Scenarios, Research Shows AWS Highlights Enterprise Governance and AI Workspace Quick Ahead of re:Invent 2026 LoanPro Integrates Amazon Bedrock to Automate Loan Servicing Workflows Google Brings Wallet App to iOS Users Across the United States Microsoft Reveals Cause of Global Outlook Outage AWS Outlines Phased Roadmap for Responsible Agentic AI Governance Google updates Gemini settings to separate chat history from AI model training Uber Eats and Zipline launch autonomous drone food delivery in Houston

MoEngage Deploys Agentic Customer Engagement Architecture on Amazon Bedrock

🧠 AI Analysis 2 min read 👁 8

Marketing platform MoEngage has introduced Merlin AI, a suite of agentic tools built using Amazon Bedrock AgentCore and the Model Context Protocol to streamline multi-channel marketing campaigns through natural language.

MoEngage Deploys Agentic Customer Engagement Architecture on Amazon Bedrock🧠AI Analysis

Photo: AWS Machine Learning Blog

Key points

  • MoEngage launched Merlin AI using Amazon Bedrock AgentCore and the Model Context Protocol.
  • The platform features four agent modes handling conversational tasks, custom workflows, and individual customer decisioning.
  • Customer Glance achieved a 38% uplift in push notification click-through rates using the agentic setup.

Marketing and product professionals often spend a significant portion of their work weeks navigating multiple software interfaces—such as analytics dashboards, content libraries, and campaign builders—before executing strategies across email, push, SMS, and WhatsApp. To address this friction, customer engagement platform MoEngage developed Merlin AI, a system of artificial intelligence agents designed to operate directly on live platform data.

By implementing the Model Context Protocol (MCP) Connector, MoEngage provides MCP-compatible assistants like Claude and ChatGPT with secure, tenant-scoped access to brand segments, campaign histories, and asset libraries. According to the company, this architecture allows software platforms to introduce a conversational layer where users describe an outcome in plain language, and an agent manages the execution steps.

Merlin AI relies on foundation models hosted on Amazon Bedrock—including Anthropic Claude Sonnet variants—for reasoning, tool-call planning, and content generation, utilizing the Amazon Bedrock AgentCore runtime. The system deploys four distinct agent modes, spanning conversational analytics, customizable continuous workflows, and individual decision-making tools for targeted offers and multi-channel delivery. MoEngage noted that early implementations have yielded measurable results, such as a 38% increase in push notification click-through rates for customer Glance.

What to watch next: Monitor whether other enterprise SaaS providers adopt MCP connectors to unify their siloed application programming interfaces into agent-ready workflows.

Source AWS Machine Learning Blog — aws.amazon.com/blogs/machine-learning/how-moengage-built-agentic-custom… ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.