<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>schristoph.online</title><link>https://schristoph.online/tags/amazontranscribe/</link><description>Personal homepage and blog of Stefan Christoph</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><copyright>Stefan Christoph. All rights reserved.</copyright><lastBuildDate>Thu, 25 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://schristoph.online/tags/amazontranscribe/index.xml" rel="self" type="application/rss+xml"/><item><title>I Rebuilt a Browser Fact-Checker on AWS, and AgentCore Web Search Was the Missing Piece</title><link>https://schristoph.online/blog/live-fact-checker-aws/?utm=rss-feed</link><pubDate>Thu, 25 Jun 2026 00:00:00 +0000</pubDate><guid>https://schristoph.online/blog/live-fact-checker-aws/</guid><description>&lt;p>🎬 Also available as a &lt;a href="https://youtu.be/x1jub37aMXM">blog walkthrough video&lt;/a> if you&amp;rsquo;d rather watch than read.&lt;/p>
&lt;div class="tldr" data-pagefind-weight="5" data-pagefind-meta="tldr" style="display:block;font-size:.875em;margin:2rem 0;border-left:4px solid #ccc;padding-left:1rem;line-height:1.5;">&lt;strong>TL;DR:&lt;/strong> I came across an open-source browser extension that fact-checks videos and live streams in real time, and I wanted to know what it would take to rebuild that idea as an AWS-native service. The answer turned out to be short, because of one recently launched piece. The pipeline is the same everywhere: transcribe, pull out the checkable claims, verify each against the web, show a verdict. The hard part has always been the verify step, which needs a model that can search the live web and cite what it found. Web Search on Amazon Bedrock AgentCore, generally available since 19 June 2026, is a managed, MCP-compatible tool that gives exactly that to any model, including Claude. With it, the build is Cognito for login, API Gateway and Lambda for the seam, Claude on Bedrock for extraction and verdict reasoning, and AgentCore Web Search for grounded, dated, cited evidence. The code is on GitHub.&lt;/div>
&lt;div class="disclaimer" style="display:block;font-size:.875em;margin:2rem 0;border-left:4px solid #ccc;padding-left:1rem;line-height:1.5;">&lt;strong>Disclaimer:&lt;/strong> I&amp;rsquo;m a solutions architect who builds things to understand them. Treat this as a builder&amp;rsquo;s field report, not authoritative guidance. The service is a proof of concept; verdicts are model-generated and you should always confirm against the cited sources. If I&amp;rsquo;ve got something wrong, tell me.&lt;/div>
&lt;h2 id="what-got-me-started">What Got Me Started&lt;/h2>
&lt;p>I came across an open-source browser extension that fact-checks YouTube videos and live streams in near real time, entirely in the browser [3]. The idea is clean and the pipeline is easy to describe: transcribe what is being said, identify the verifiable claims inside the transcript, verify each claim against the web, and highlight the result inline as the video plays. It leans on Google Gemini&amp;rsquo;s built-in search grounding for the verification step, and it does the job well for a single user with a personal API key.&lt;/p></description></item></channel></rss>