Building a Fraud Detection Console With MongoDB and Mastra

This workshop covers building Marshal, a fraud investigation console powered by MongoDB Atlas and Mastra, with hybrid search, graph lookups, and durable workflows for human review. See how it brings scattered evidence together to approve, reject, or escalate transactions while preserving an audit trail of the evidence and reasoning behind each decision. Hosted by: Brandon Barros, Founding Product Advocate @ Mastra Nina Lopatina, Staff Developer Advocate @ MongoDB CHAPTERS 00:00 Introductions and workshop overview 02:22 The fraud detection problem and where agents fit 09:49 Marshal walkthrough: approvals, rejections, and human review 18:50 Modeling evidence and retrieval in MongoDB Atlas 20:34 Code walkthrough: rank fusion, graph lookup, and change streams 25:37 Mastra agents and durable workflows with suspend/resume 28:00 Moving from a demo to production 30:43 Observability, evals, agent learning, and PII controls 35:37 Consolidating operational, vector, and graph data in MongoDB 37:09 Resources and Q&A: policy updates, embeddings, and agent learning WHAT IS MASTRA Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development, from prototype to production. 📚 MASTRA RESOURCES Website: https://mastra.ai X: https://x.com/mastra_ai Discord: https://mastra.ai/community/discord GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of... Patterns for Building AI Agents (Book): https://mastra.ai/books/patterns-of-b...