Nasi Chaudhari - AI Meets Serverless: Automating Receipt Intelligence with AWS Lambda & Textract

#LambdaConf2025 took place in Estes Park Colorado this past May 12th and 13th. Learn about the sponsors that made it happen: Ziverge Transformative Tech for Modern Challenges https://www.ziverge.com/ Urbit Foundation Leave the Internet Behind https://urbit.org/ Golem Cloud Deploy secure AI apps that run reliably https://www.golem.cloud/ Platonic Systems Solving your toughest software problems https://platonic.systems/ Abstract for this talk: Imagine uploading a receipt and instantly getting a structured, searchable summary in your inbox — no manual data entry, no backend server to manage. In this session, we’ll explore how to build an intelligent, end-to-end receipt processing system using AWS Lambda, Amazon Textract, DynamoDB, and SES — all in a fully serverless architecture.You'll see how we combine the power of AI-driven document analysis with the scalability and simplicity of serverless computing. We'll break down the architecture, dive into key code patterns, and cover how to handle real-world challenges like messy input data, failed extractions, and asynchronous workflows.Whether you're curious about event-driven design, AI integrations, or building real-world AWS Lambda apps, this talk will leave you with patterns you can immediately apply to your own projects. What you'll learn: - Architecting serverless workflows with S3 triggers and Lambda functions - Extracting structured data from receipts using Amazon Textract - Storing and querying data efficiently in DynamoDBSending formatted email notifications with SES - Tips for handling errors, retries, and scaling issues in production