Finops on Start AI Tools - Presented by Intent Solutionshttps://startaitools.com/tags/finops/Recent content in Finops on Start AI Tools - Presented by Intent SolutionsHugoen-USIntent Solutions. All rights reserved.Sat, 27 Jun 2026 07:13:58 -0600The LLM Should Never Do the Mathhttps://startaitools.com/posts/llm-never-does-the-math/Fri, 26 Jun 2026 08:00:00 -0500https://startaitools.com/posts/llm-never-does-the-math/<p>A CFO will not act on a number an LLM eyeballed. They will not act on a number the model &ldquo;estimated&rdquo; by reasoning over a usage dump. And they should not — because the moment a language model emits a dollar figure it computed itself, that figure is a guess wearing the costume of a fact.</p> <p>This is the design constraint behind <code>databricks-cost-leak-hunter</code>, the pilot skill of the databricks-pack v2 rebuild shipped in the claude-code-plugins marketplace (<a href="https://github.com/jeremylongshore/claude-code-plugins">PR #906</a>). Given a live, authenticated Databricks workspace, it surfaces real cost leaks across four named categories, ranks them by monthly dollar impact, and emits a report a finance reader can act on. The marketplace validator graded it B (88/100, zero errors). The SKILL.md is 329 lines. The single most important thing in it is a rule the model is structurally prevented from breaking: <strong>the LLM never does the dollar arithmetic.</strong></p>