# How are scores calculated? Every lead in Leadbay has a **score from 0 to 99**. Higher means more relevant to you. ### What the score measures The score reflects how similar a lead is to the leads that have worked for you — your **won deals** and **liked leads**. It's computed using AI embedding models that capture deep patterns beyond simple keyword matching. ### What influences the score * **Won deals**: the strongest signal. Leads similar to your past wins score highest. * **Liked leads**: likes tell the model what you find relevant. * **Qualification answers**: if the [AI Assistant](/doc/product-guides/ai-assistant.md) is configured, positive answers to your questions boost the score. * **Active lens**: each lens has its own AI model, so the same lead may score differently in different lenses. ### How to improve your scores * **Like and dislike** leads regularly in Discover — this trains the model * **Update lead statuses** (won/lost) — this is the best signal * **Configure qualification questions** — adds another scoring dimension * **Use focused lenses** — a lens targeting one market segment gives more precise scores than a broad one The score recalculates periodically as the model learns from your actions. --- # Agent Instructions: 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: ``` GET https://docs.leadbay.app/doc/q-and-a/how-are-scores-calculated.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.