> ## Documentation Index
> Fetch the complete documentation index at: https://docs.usepropane.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Eval

> Continuous scoring that measures how well your canvas is supported by evidence

**Eval** is a continuous scoring system that runs from the moment a canvas is created. It measures how well your canvas is supported by the evidence and context you have provided — and nudges you towards a stronger document.

Eval lives in a **drawer at the bottom of the canvas**. Click it to expand the full breakdown. You will see an overall readiness score, a status label, and a summary of what is missing. Below that, each dimension is rated individually — **Strong**, **Partial**, or **Weak** — with a short explanation of why.

Eval looks at: **Problem & Goal**, **Feature Scope**, **Technical Context**, **User Evidence**, and **Competitive Reference**. The score updates as you add more context or refine the canvas.

## Related

* [How the AI responds](/chat/how-ai-responds)
* [Signals](/signals/where-signals-come-from)