<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Engineering on Software Engineering, Architecture and AWS Serverless Technology from makit</title><link>https://makit.net/tags/engineering/</link><description>Recent content in Engineering on Software Engineering, Architecture and AWS Serverless Technology from makit</description><generator>Hugo -- gohugo.io</generator><language>en</language><lastBuildDate>Mon, 28 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://makit.net/tags/engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>Give the agent a way to find product context</title><link>https://makit.net/blog/give-the-agent-a-way-to-find-product-context/</link><pubDate>Mon, 28 Sep 2026 00:00:00 +0000</pubDate><guid>https://makit.net/blog/give-the-agent-a-way-to-find-product-context/</guid><description>An agent can only check its work against the part of the product it can see.
I think a lot of developers give an agent one repository and a problem, then let it start cooking. If the other repositories that talk to it are missing, then the agent doesn&amp;rsquo;t have the context of changes happening across them. Before asking for a bigger prompt, give it a way to find the work around the change.</description></item></channel></rss>