<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Code-Intelligence on Blackwell Systems</title><link>https://blog.blackwell-systems.com/tags/code-intelligence/</link><description>Recent content in Code-Intelligence on Blackwell Systems</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 15 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.blackwell-systems.com/tags/code-intelligence/index.xml" rel="self" type="application/rss+xml"/><item><title>agent-lsp: Reliable Code Intelligence for AI Agents via MCP and LSP</title><link>https://blog.blackwell-systems.com/posts/agent-lsp/</link><pubDate>Wed, 15 Apr 2026 00:00:00 +0000</pubDate><guid>https://blog.blackwell-systems.com/posts/agent-lsp/</guid><description>I needed AI agents to reliably rename symbols, find references, and check diagnostics without silent failures. The existing MCP-LSP tools were stateless, feature-poor, and untested. So I built agent-lsp — a persistent session runtime with 50 tools, 30 CI-verified languages, speculative execution, and a skill layer that makes correct tool sequences happen automatically.</description></item></channel></rss>