> For the complete documentation index, see [llms.txt](https://docs.aloop.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.aloop.icustomer.ai/iharness/plays-to-decisions.md). # How plays become decisions How iHarness picks a play: diagnosis over lookup, capability before commitment, and decisions as the output. iHarness does not pick plays from a menu. It diagnoses. ## Every play pulls a lever A play is not just a description of work; it declares the **lever** it pulls, the mechanism by which it moves a KPI. Several plays can move the same number by different levers: one fills the top of the funnel, another accelerates what is already in it, a third stops waste. Naming the lever is what turns selection into a diagnosis instead of a lookup. ## Diagnosis, not lookup When a KPI is off, iHarness asks *why* before asking *what to run*: which cause is present, which signal detects it, and which play addresses that cause. Two workspaces with the same slow number can get different plays, because the cause differs. Where the system cannot diagnose, it says so plainly and falls back honestly, rather than dressing a guess as a diagnosis. ## Capability before commitment The order surprises people: the play portfolio is chosen **before** the target is finalized. iHarness sizes a target from what the serviceable plays can actually deliver, never from the benchmark alone. Nobody should be asked to commit to a number before being shown what could move it. ## Running a play produces decisions A play in motion is a stream of [decisions](/concepts/decisions-and-traces.md): which records are in scope, which get spend, which channel, which budget. Each one spends something finite, states what it expects, and writes its trace. That is the contract that makes a play accountable: not "it ran," but "here is what it chose, what it spent, and what came back." ## And outcomes come back around Outcomes credit the decisions that caused them, decisions credit the target, and what a closed target proves becomes evidence for choosing and sizing the next play. See [Goals, KPIs and targets](/iharness/goals-kpis-targets.md). --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.aloop.icustomer.ai/iharness/plays-to-decisions.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.