Urgent.News

What's breaking now, across thousands of outlets.

AI

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.

MoEngage, a customer engagement platform utilized by over 1,350 consumer brands across multiple channels, has developed an agentic system to streamline marketing and product team workflows. Traditionally, teams would navigate various tools to plan weekend flash sales, collect data, and build campaigns across email, push, SMS, WhatsApp, and RCS. To address this challenge, MoEngage built Merlin AI, a suite of AI agents capable of working with live platform data.

The four agent modes in Merlin AI include Copywriter for generating personalized copy, Designer for creating marketing visuals, Segment Assist for converting plain-language audience descriptions into targeted segments, and Jinja Assist for converting natural-language requests into working Jinja and Liquid markup. Additionally, Flow Assist creates responsive, accessible HTML templates for in-app messages and Flow Assist converts high-level ideas into deployable customer journeys.

Conversational agents allow users to ask plain language questions and receive relevant answers or take appropriate actions. Campaign Insights Agent, embedded on the analytics page, delegates tasks to sub-agents that perform analysis, diagnose issues, compare performance, and format findings into clear answers. Custom agents enable lifecycle and CRM teams to design agents that continuously operate within predefined rules, providing an activity log for transparency and audit purposes.

Decisioning agents, acting on an individual customer level, determine messaging, frequency, and channel based on product and marketing team-defined content, goals, and guardrails. Offer Decisioning selects the best offer across web and app surfaces, while Campaign Decisioning delivers personalized decisions across email, push, SMS, and WhatsApp.

The architecture of MoEngage's system is divided into four layers: Clients, MCP Server, MCP Ser, and Foundation Models and AgentCore. Clients include MoEngage's internal agents and external MCP clients like Claude and ChatGPT, connected through the MoEngage MCP Connector. MCP Server facilitates secure, tenant-scoped access to data, ensuring isolation between tenants.

MoEngage's implementation of Amazon Bedrock and AgentCore enables a seamless, integrated approach to customer engagement, reducing the need for teams to switch between different tools and enhancing overall efficiency.

Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Every outlet that reported this, and when →

Read the original at aws.amazon.com →

More in AI

More from Monday 16 November →