<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai on Connor Charles</title><link>https://ccharlesgb.github.io/cc-portfolio/tags/ai/</link><description>Recent content in Ai on Connor Charles</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 22 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://ccharlesgb.github.io/cc-portfolio/tags/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Hack Diary: Natural Language Queries of Data Using a Semantic Layer</title><link>https://ccharlesgb.github.io/cc-portfolio/post/natural-language-queries/</link><pubDate>Mon, 22 Jun 2026 00:00:00 +0000</pubDate><guid>https://ccharlesgb.github.io/cc-portfolio/post/natural-language-queries/</guid><description>&lt;p&gt;Recently, my team at Autotrader ran a hack on ways to improve the experience of the data platform for our colleagues. The aim of this hack wasn&amp;rsquo;t necessarily to produce production-ready software, but to give the team exposure to AI-based workflows and semantic layers. One of the biggest pain points we have is that we have a &lt;strong&gt;lot&lt;/strong&gt; of data, dashboards and reports and it can be hard to find the right one. Especially in meetings where sometimes someone will ask &amp;ldquo;How many X did we have last week?&amp;rdquo; and then someone might have to step back from the conversation and find the right dashboard by which point the meeting has already moved on.&lt;/p&gt;</description></item></channel></rss>