<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AWS on Inquisitive M365</title><link>https://thomasdaly.net/tag/aws/</link><description>Recent content in AWS on Inquisitive M365</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Tom Daly</copyright><lastBuildDate>Wed, 05 Mar 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://thomasdaly.net/tag/aws/index.xml" rel="self" type="application/rss+xml"/><item><title>Building a Two-Stage AI Pipeline for Invoice Processing with AWS Textract and Amazon Bedrock</title><link>https://thomasdaly.net/2025/03/04/textract-plus-bedrock-two-stage-ai-pipeline/</link><pubDate>Wed, 05 Mar 2025 00:00:00 +0000</pubDate><guid>https://thomasdaly.net/2025/03/04/textract-plus-bedrock-two-stage-ai-pipeline/</guid><description>How I built a serverless pipeline using AWS Textract for OCR and Amazon Bedrock for AI normalization to extract structured data from invoices across hundreds of different vendor formats.</description></item></channel></rss>