> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/understand-lleverage/readme/measuring-improvement.md). # Operational metrics Running work automatically is not the same as improving the operation. The outcome that matters is whether the operation itself gets better. Use operational measures such as **cost, mistakes and bottlenecks** to evaluate whether automation improves the process. ## Cost How much human and system effort does the work consume? Automation can reduce repetitive handling, re-keying, chasing and other work that consumes time without requiring much judgement. ## Mistakes Where does work need correction, rework or recovery? Useful measures depend on the operation, but may include first-time-right rates, correction volume, failed checks or the amount of work returned for rework. ## Bottlenecks Where does work wait, get blocked or fail to keep pace with the business? This can include queues waiting for a particular person, missing information, supplier responses, approvals or systems that cannot keep up with demand. ## Measurement criteria Different operations will have more specific measures, such as processing time, touch rate, exception volume or turnaround time. The purpose of measurement is to distinguish automation that merely moves work around from automation that genuinely improves the operation. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.lleverage.ai/understand-lleverage/readme/measuring-improvement.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.