> For the complete documentation index, see [llms.txt](https://docs.icustomer.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.icustomer.ai/measurement-and-outcomes/decision-quality.md). # Decision quality A different question than did it work: was the judgment good, measured as expected versus actual. "Did the outcome happen?" and "was the decision good?" are different questions. A good decision can lose to bad luck; a bad one can win by accident. Decision quality is the discipline of grading the judgment itself, and it is only possible because every decision states, up front, what it expects. ## Expected versus actual Each decision carries a typed expectation: which number moves, by how much, by when, at what spend. The outcome arrives in the same shape, and the difference is the grade. Aggregated over time, the grades answer questions no channel dashboard can: * Where is the system systematically over-confident, or under-confident? * Which kinds of decisions, which channels, which cohorts, which plays, does it judge well, and where is it still guessing? * What did we spend, grouped by what we were trying to do? ## The unmeasured decision The worst grade is no grade. A wrong decision teaches something; an unmeasured one spent something real and taught nothing. Decisions whose expected-by date passed with no outcome recorded are surfaced as their own list, not buried, because "we never found out" is a finding. ## Why this matters to you Decision quality is the honest basis for [autonomy](/pulse/autopilot-vs-approval-first.md): you widen the gates where the judgment is measurably good, and keep approvals where it is not. Trust built on grades beats trust built on demos. --- # 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.icustomer.ai/measurement-and-outcomes/decision-quality.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.