<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AWS Continuum on The road</title><link>https://kane.mx/tags/aws-continuum/</link><description>Recent content in AWS Continuum on The road</description><generator>Hugo -- gohugo.io</generator><language>en</language><lastBuildDate>Wed, 18 Nov 2026 12:00:00 +0800</lastBuildDate><atom:link href="https://kane.mx/tags/aws-continuum/index.xml" rel="self" type="application/rss+xml"/><item><title>AWS Continuum Experiment: Findings, Fixes, and Cost</title><link>https://kane.mx/posts/2026/aws-continuum-mem9-security-review/</link><pubDate>Wed, 18 Nov 2026 12:00:00 +0800</pubDate><guid>https://kane.mx/posts/2026/aws-continuum-mem9-security-review/</guid><description>
&lt;p>I connected &lt;a href="https://aws.amazon.com/continuum/">AWS Continuum&lt;/a> to my &lt;a href="https://kane.mx/posts/2026/self-hosted-agent-memory-mem9-on-aws/">mem9 deployment&lt;/a> to see whether an AI security service could move beyond reporting vulnerabilities and help deliver verified fixes. It did produce useful remediation work. It also exposed two costs I had underestimated: the engineering needed to admit generated patches safely, and the inference cost of a full repository scan.&lt;/p>
&lt;p>The experiment covered a codebase of roughly 233,000 lines across 704 files. My investigation put &lt;strong>one full scan at roughly $250–370 in inference charges&lt;/strong>, based on approximate scan-window attribution. That is an observation from this workload, not a fixed price per scan or a quote for another repository.&lt;/p>
&lt;p>&lt;a href="https://kane.mx/posts/2026/aws-continuum-mem9-security-review/">Read More&lt;/a>&lt;/p></description></item></channel></rss>