<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Why Katalyst? on Katalyst Documentation</title><link>https://deploy-preview-124--stately-starburst-216875.netlify.app/deep-dives/why-katalyst/</link><description>Recent content in Why Katalyst? on Katalyst Documentation</description><generator>Hugo</generator><language>en-us</language><atom:link href="https://deploy-preview-124--stately-starburst-216875.netlify.app/deep-dives/why-katalyst/index.xml" rel="self" type="application/rss+xml"/><item><title>What is curation?</title><link>https://deploy-preview-124--stately-starburst-216875.netlify.app/deep-dives/why-katalyst/what-is-curation/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://deploy-preview-124--stately-starburst-216875.netlify.app/deep-dives/why-katalyst/what-is-curation/</guid><description>&lt;h1 id="what-is-curation"&gt;What is curation?&lt;a class="anchor" href="#what-is-curation"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;!--Motivate the question--&gt;
&lt;p&gt;If AI systems are going to curate content effectively, they need a clear target: what counts as curation, and what good curation should accomplish.&lt;/p&gt;
&lt;!-- Provide several specific and diverse examples of curation work; bullet list sentence fragments --&gt;
&lt;p&gt;Let&amp;rsquo;s start from examples. The work of curation shows up in many practical tasks:&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;summarizing the useful parts of a conversation thread in a document that people can find later&lt;/li&gt;
&lt;li&gt;grouping related notes so they are easier to browse&lt;/li&gt;
&lt;li&gt;adding dates, owners, tags, or status labels so people know what they are looking at&lt;/li&gt;
&lt;li&gt;rewriting headings so a reader can scan the page before committing to it&lt;/li&gt;
&lt;li&gt;removing duplicate or stale material&lt;/li&gt;
&lt;/ul&gt;
&lt;!-- Transition and provide my definition --&gt;
&lt;p&gt;These tasks look different, but they all share the same purpose: making content usable.&lt;/p&gt;</description></item><item><title>Internal consistency</title><link>https://deploy-preview-124--stately-starburst-216875.netlify.app/deep-dives/why-katalyst/internal-consistency/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://deploy-preview-124--stately-starburst-216875.netlify.app/deep-dives/why-katalyst/internal-consistency/</guid><description>&lt;h1 id="internal-consistency"&gt;Internal consistency&lt;a class="anchor" href="#internal-consistency"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;!-- Introduce the definition --&gt;
&lt;p&gt;Consistency means being free from internal contradiction. On its surface, this seems simple: the knowledge base can&amp;rsquo;t say &amp;ldquo;A is true&amp;rdquo; in one place and &amp;ldquo;A is false&amp;rdquo; in another.&lt;/p&gt;
&lt;!-- Distinguish between content claims and structural claims --&gt;
&lt;h2 id="content-claims-vs-structural-claims"&gt;Content claims vs structural claims&lt;a class="anchor" href="#content-claims-vs-structural-claims"&gt;#&lt;/a&gt;&lt;/h2&gt;
&lt;p&gt;However, there&amp;rsquo;s some subtlety here. Imagine a folder containing customer feedback interviews. In one transcript, customer A says, &amp;ldquo;this product is amazing!&amp;rdquo; In another, customer B says &amp;ldquo;the product is terrible.&amp;rdquo; Those statements are in direct contradiction, but is the knowledge base inconsistent?&lt;/p&gt;</description></item><item><title>Completeness</title><link>https://deploy-preview-124--stately-starburst-216875.netlify.app/deep-dives/why-katalyst/completeness/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://deploy-preview-124--stately-starburst-216875.netlify.app/deep-dives/why-katalyst/completeness/</guid><description>&lt;h1 id="completeness"&gt;Completeness&lt;a class="anchor" href="#completeness"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;!-- Draft this section --&gt;
&lt;p&gt;Completeness means covering all the relevant material within some scope.&lt;/p&gt;
&lt;p&gt;The scope matters. A knowledge base does not need to contain every true fact in the world. It needs to contain the material required by the purpose it claims to serve.&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Claims about ordering rely on claims about completeness&lt;/li&gt;
&lt;/ul&gt;</description></item><item><title>Up-to-dateness</title><link>https://deploy-preview-124--stately-starburst-216875.netlify.app/deep-dives/why-katalyst/up-to-dateness/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://deploy-preview-124--stately-starburst-216875.netlify.app/deep-dives/why-katalyst/up-to-dateness/</guid><description>&lt;h1 id="up-to-dateness"&gt;Up-to-dateness&lt;a class="anchor" href="#up-to-dateness"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;p&gt;Up-to-dateness is the guarantee of external consistency: the state of the content accurately reflects the state of the real world at some point in time. A knowledge base can be internally consistent and complete within its stated scope while still being wrong, because the world changed since the content was last updated.&lt;/p&gt;
&lt;p&gt;That makes up-to-dateness different from the other two criteria. It cannot be guaranteed from inside the content alone. It requires contact with an external source of truth: an event stream, a periodic refresh, a source-system query, a human review, or some other verification process. A curated system can record timestamps, sources, freshness windows, and update rules, but the guarantee comes from the process that reconnects the content to the world.&lt;/p&gt;</description></item><item><title>Progressive operations</title><link>https://deploy-preview-124--stately-starburst-216875.netlify.app/deep-dives/why-katalyst/progressive-operations/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://deploy-preview-124--stately-starburst-216875.netlify.app/deep-dives/why-katalyst/progressive-operations/</guid><description>&lt;h1 id="progressive-operations"&gt;Progressive Operations&lt;a class="anchor" href="#progressive-operations"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;p&gt;&lt;em&gt;How storage backends evolve as query complexity grows. Each tier unlocks new operations, but requires structural commitments the previous tier doesn&amp;rsquo;t.&lt;/em&gt;&lt;/p&gt;
&lt;p&gt;Structuredness comes down to which operations a backend supports, and schemas and checks are the means: enforcing checks is what makes new operations available. The core thesis follows: many knowledge systems start as filesystems and progressively acquire database-like structure. The progression isn&amp;rsquo;t arbitrary, each tier is driven by a class of operations that can&amp;rsquo;t be satisfied at the previous level.&lt;/p&gt;</description></item></channel></rss>