<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agentic-Workflows on CuraDevOps</title><link>https://curadevops.metacog.co.kr/tags/agentic-workflows/</link><description>Recent content in Agentic-Workflows on CuraDevOps</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 17 Jul 2026 12:03:24 +0000</lastBuildDate><atom:link href="https://curadevops.metacog.co.kr/tags/agentic-workflows/index.xml" rel="self" type="application/rss+xml"/><item><title>GitLab 19.2 Custom Flows reach GA: agentic multi-step delivery pipelines</title><link>https://curadevops.metacog.co.kr/insights/2026-07-17-turn-multi-step-software-delivery-into-agentic-flows-you-can/</link><pubDate>Fri, 17 Jul 2026 12:03:24 +0000</pubDate><guid>https://curadevops.metacog.co.kr/insights/2026-07-17-turn-multi-step-software-delivery-into-agentic-flows-you-can/</guid><description>&lt;ul>
&lt;li>&lt;strong>Platform/SRE — Skip&lt;/strong>&lt;/li>
&lt;li>&lt;strong>CI/CD — Plan:&lt;/strong> Custom Flows are now GA in GitLab 19.2, enabling event-triggered, AI-driven multi-step pipeline sequences (e.g., analyze failure → generate fix → commit → notify). Teams on GitLab should evaluate whether encoding trusted delivery sequences as Flows reduces manual handoffs and pipeline runbook debt.&lt;/li>
&lt;li>&lt;strong>Leader — Learn:&lt;/strong> GitLab&amp;rsquo;s agentic flow model represents a meaningful shift in how AI is integrated into the delivery lifecycle — moving from single-turn chat to orchestrated, human-approved sequences. Worth tracking as input to dev-platform strategy and AI tooling evaluation, but no strategic decision is forced by this release.&lt;/li>
&lt;li>&lt;strong>Signals:&lt;/strong> GA announcement&lt;/li>
&lt;/ul></description></item></channel></rss>