<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>polischuks.dev — Blog</title><description>Notes on building production AI agent systems: architecture, pipelines, MCP, retrieval and the operational edges.</description><link>https://polischuks.dev/</link><language>en-US</language><item><title>Designing a multi-agent pipeline</title><link>https://polischuks.dev/blog/designing-a-multi-agent-pipeline/</link><guid isPermaLink="true">https://polischuks.dev/blog/designing-a-multi-agent-pipeline/</guid><description>The agent is rarely the hard part of an agent system. The queue, the budget, the durable record and the independent check are — here is what I keep across them.</description><pubDate>Tue, 06 Oct 2026 00:00:00 GMT</pubDate><category>agents</category><category>architecture</category><category>mcp</category></item><item><title>Notes on MCP servers</title><link>https://polischuks.dev/blog/notes-on-mcp-servers/</link><guid isPermaLink="true">https://polischuks.dev/blog/notes-on-mcp-servers/</guid><description>The protocol is the easy part. The discipline is not rebuilding your product inside the server — keep it a thin proxy over the system you already run.</description><pubDate>Tue, 06 Oct 2026 00:00:00 GMT</pubDate><category>mcp</category><category>agents</category></item></channel></rss>