https://ezablocki.com/tags/llmops/ Recent content in LLMOps on Eugeniusz Zabłocki Blog Hugo -- gohugo.io en-us © Eugeniusz Zabłocki Mon, 18 May 2026 10:00:00 +0200 https://ezablocki.com/posts/sentinel-ai-part-1-map-reduce/ Mon, 18 May 2026 10:00:00 +0200 https://ezablocki.com/posts/sentinel-ai-part-1-map-reduce/ If you’ve ever built a prototype of an LLM agent, you probably started with a clean, sequential flow. A user inputs a file, your agent processes it item by item in a standard Python loop, and returns a response. It works beautifully on your local machine with three test cases. Then, you hit production. Suddenly, a user uploads a manifest file with 60 dependencies. Processing them sequentially means your application locks up, the latency spikes linearly, and your time-to-first-token (TTFT) degrades into minutes.