<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai-Assisted on CuraDevOps</title><link>https://curadevops.metacog.co.kr/tags/ai-assisted/</link><description>Recent content in Ai-Assisted on CuraDevOps</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 21 Aug 2026 11:18:28 +0000</lastBuildDate><atom:link href="https://curadevops.metacog.co.kr/tags/ai-assisted/index.xml" rel="self" type="application/rss+xml"/><item><title>GitLab 19.3 Flow Creator agent: natural-language flow authoring</title><link>https://curadevops.metacog.co.kr/insights/2026-08-21-build-custom-flows-in-minutes-with-the-flow-creator-agent/</link><pubDate>Fri, 21 Aug 2026 11:18:28 +0000</pubDate><guid>https://curadevops.metacog.co.kr/insights/2026-08-21-build-custom-flows-in-minutes-with-the-flow-creator-agent/</guid><description>&lt;ul>
&lt;li>&lt;strong>Platform/SRE — Skip&lt;/strong>&lt;/li>
&lt;li>&lt;strong>CI/CD — Plan:&lt;/strong> New GA capability in GitLab 19.3 that lets domain experts author Custom Flows via natural language instead of learning the Flow Registry YAML schema; worth evaluating this quarter to reduce the bottleneck between process knowledge and automation authorship.&lt;/li>
&lt;li>&lt;strong>Leader — Skip&lt;/strong>&lt;/li>
&lt;li>&lt;strong>Signals:&lt;/strong> GitLab 19.3 reaches EOL in 90d (2026-11-19)&lt;/li>
&lt;/ul></description></item><item><title>GitLab Duo Security Review Flow (beta) targets logic-flaw blind spots</title><link>https://curadevops.metacog.co.kr/insights/2026-07-17-gitlab-duo-security-review-spots-logic-flaws-scanners-miss/</link><pubDate>Fri, 17 Jul 2026 12:03:24 +0000</pubDate><guid>https://curadevops.metacog.co.kr/insights/2026-07-17-gitlab-duo-security-review-spots-logic-flaws-scanners-miss/</guid><description>&lt;ul>
&lt;li>&lt;strong>Platform/SRE — Skip&lt;/strong>&lt;/li>
&lt;li>&lt;strong>CI/CD — Learn:&lt;/strong> Public beta feature worth tracking for GitLab shops — it layers intent-based analysis over existing SAST to catch authorization and workflow flaws before merge, but it&amp;rsquo;s pre-GA so nothing to enable in production pipelines yet.&lt;/li>
&lt;li>&lt;strong>Leader — Learn:&lt;/strong> AI-assisted logic-flaw detection is a meaningful gap-fill beyond signature-based scanners; worth monitoring as it approaches GA to assess whether it changes the org&amp;rsquo;s AppSec toolchain or reduces security-review cycle time.&lt;/li>
&lt;/ul></description></item></channel></rss>