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

# Introduction

> Learn what evaluators are and how they help measure the quality of AI-generated educational materials through pedagogical alignment assessment.

<Note>
  Evaluator notebooks, prompts, and SDKs live in the
  [`evaluators`](https://github.com/learning-commons-org/evaluators) ↗
  GitHub repository.
</Note>

## What evaluators do

Evaluators measure the quality of AI-generated educational content by assessing specific dimensions of text and identifying areas for improvement.

Evaluators help edtech developers reliably assess their LLM outputs and build evidence-based tools that reinforce student learning and whole child development.

| Evaluator family | Description |
| :- | :- |
| [Text Complexity evaluators](/evaluators/text-complexity-evaluators/introduction) | Assess the qualitative text complexity of a passage, often for a particular grade level |
| [Feedback evaluators](/evaluators/feedback-evaluators/introduction) | Assess the quality of feedback on a student's response to a task goal |
| [Academic Standards evaluators](/evaluators/academic-standards-evaluators/introduction) | Assess the alignment of educational content to standards |
| [Durable Skills evaluators](/evaluators/durable-skills-evaluators/introduction) | Assess student work against constructs like critical thinking, argumentation, or reasoning |

<Note>
  Explore [Use cases](/evaluators/understanding-evaluators/use-cases) for
  evaluators while testing, refining, or scaling AI-generated content.
</Note>

## How to access Evaluators

| Access method | When to use |
| :- | :- |
| [Evaluators playground](/evaluators/getting-started/quickstart#evaluators-playground) | For a quick demo of how evaluators work |
| [SDK](/evaluators/getting-started/quickstart#sdk) | To integrate into your TypeScript or Python project |
| [Python notebook](/evaluators/getting-started/quickstart#python-notebooks) | For quick prototyping |

## Our approach

Learning Commons collaborates closely with pedagogical experts to define, test, and build our evaluators.

We follow a research-informed process to develop evaluators that are firmly anchored in learning science:

<Frame>
  <img
    src="https://mintcdn.com/czi-60a2a443/UtkD6p7UkcR_E40q/images/evaluators/our-approach-to-building-evaluators.svg?fit=max&auto=format&n=UtkD6p7UkcR_E40q&q=85&s=875da5467c3f0007dadd426fcd4e45be"
    alt="Diagram showing the AIDT process for designing and validating
evaluators"
    width="2276"
    height="583"
    data-path="images/evaluators/our-approach-to-building-evaluators.svg"
  />
</Frame>

* We build alongside experts in learning science and rubric development (e.g., [Student Achievement Partners (SAP)](https://learnwithsap.org/) ↗, [CAST](https://www.cast.org/) ↗, and [Achievement Network (ANet)](https://www.achievementnetwork.org/) ↗).
* We translate expert insight into ground-truth datasets that reflect real teaching and learning principles.
* We develop, validate, and ship software that evaluates text the way an expert would.

## Related topics

<CardGroup cols={2}>
  <Card title="Use cases" icon="lightbulb" href="/evaluators/understanding-evaluators/use-cases">
    Explore product, model selection, runtime, and trust workflows for
    evaluators.
  </Card>

  <Card title="Core concepts" icon="lightbulb" href="/evaluators/understanding-evaluators/core-concepts">
    Learn how evaluators, dimensions, rubrics, and accuracy work together.
  </Card>

  <Card title="Quickstart" icon="rocket" href="/evaluators/getting-started/quickstart">
    Run an evaluator in the Evaluators playground, a Python notebook, or with
    the SDK.
  </Card>
</CardGroup>