> For the complete documentation index, see [llms.txt](https://docs.interactive.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.interactive.ai/improvement/scores.md).
# Scores
A score is a single evaluation attached to a trace or an observation. Everything that judges quality on the platform produces one: evaluators running automatically, people reviewing work by hand in Annotations, and your own code through the SDK. The Source column tells you which produced a given score.
Each score carries a name, a data type, and a value. The name comes from whatever produced it, so an evaluator's `answer_quality` and a reviewer's `helpfulness` sit side by side in the same table. The data type says how to read the value: a number, one of a fixed set of categories, or true and false.
This page is the only place the whole project's quality signal sits in one table, which makes it where you go to compare across evaluators and reviewers rather than to judge a single request.
### Following a score
A score means little on its own, so most columns lead somewhere.
Opening the trace a score belongs to lands on that trace's Scores tab, with the value alongside the comment whoever produced it left behind.
Opening the user shows their whole history: their traces, sessions, and every score they have accumulated.
---
# 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.interactive.ai/improvement/scores.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.
