<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Knowledge-Base on Rishi's Blog</title><link>https://blog.bansalai.com/tags/knowledge-base/</link><description>Recent content in Knowledge-Base on Rishi's Blog</description><generator>Hugo</generator><language>en-US</language><copyright>&amp;copy; 2026 Rishi Bansal</copyright><lastBuildDate>Tue, 04 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.bansalai.com/tags/knowledge-base/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM-Wiki as a Milestone Compiler for Agent Projects</title><link>https://blog.bansalai.com/posts/llm-wiki-milestone-compiler/</link><pubDate>Tue, 04 Aug 2026 00:00:00 +0000</pubDate><guid>https://blog.bansalai.com/posts/llm-wiki-milestone-compiler/</guid><description>&lt;p&gt;Agents operating on codebases run into the same wall: context collapses after a milestone. Teams rely on ephemeral files like &lt;code&gt;plan.md&lt;/code&gt; for in-flight work, but once the sprint ends, that memory is buried or lost. A compiled wiki solves this by forcing a durable synthesis of decisions, facts, and architecture at gate intervals. The result is a structured, typed knowledge base that reduces query-time token costs and prevents agents from re-deriving knowledge on every turn. Here is how to build the pattern, where it breaks at scale, and the infrastructure tradeoffs that keep it honest.&lt;/p&gt;</description></item></channel></rss>