Evaluation

Once you’ve configured your evaluator, you can start evaluating text inputs for grade level appropriateness:

example.ts

const evaluator = new GradeLevelAppropriatenessEvaluator({
  googleApiKey: process.env.GOOGLE_API_KEY,
});

await evaluator.evaluate({ text: "The cat's out of the bag now." });

Inputs

Each evaluator requires different input fields when invoking evaluate().

Student-Facing Text

Grade Level Appropriateness takes { text }:

Field	Type	Description
`text`	`string`	Informational text to evaluate. 10–10,000 characters

All other Student-Facing Text evaluators take { text, grade_level }:

Field	Type	Description
`text`	`string`	Informational text to evaluate. Length limits vary by evaluator (typically 1–10,000 characters)
`grade_level`	`"3" \| "4" \| "5" \| "6" \| "7" \| "8" \| "9" \| "10" \| "11" \| "12"`	Target student grade as a string literal. A number or a word like `"fifth"` does not compile; a string from a form or database needs narrowing before you pass it

Feedback

Feedback evaluators take { student_text, feedback_text }:

Field	Type	Description
`student_text`	`string`	Student’s written response. 1–10,000 characters
`feedback_text`	`string`	Teacher or AI feedback to evaluate. 1–10,000 characters

await evaluator.evaluate({
  student_text:
    "Some people think AI-powered pets are a good alternative to real pets because they could help around the house etc.",
  feedback_text:
    "You're right, the AI pets could help around the house. Can you find some other details from the article that you could add to make your claim stronger?",
});

Academic Standards

Academic Standards evaluators take { question, statement_code, jurisdiction }:

Field	Type	Description
`question`	`string`	Math assessment question to evaluate. 1–10,000 characters
`statement_code`	`string`	Math standard code to evaluate against (e.g., `"3.MD.C.7.d"`, `"K.CC.A.1"`). 1–50 characters
`jurisdiction`	`Jurisdiction` ↗	Standards jurisdiction (`JurisdictionENUM`). Use `Jurisdiction.MultiState` for

import { Jurisdiction } from "@learning-commons/evaluators";

await evaluator.evaluate({
  question: "A playground is shaped like an L. What is its area?",
  statement_code: "3.MD.C.7.d",
  jurisdiction: Jurisdiction.MultiState,
});

Math Standards Alignment also supports bulk methods:

evaluateItems for question–standard pairs
evaluateByGradeLevel for a question bank against every standard in a grade

Output

All Student-Facing Text, Feedback, and Academic Standards evaluators have the following output fields:

Field	Type	Description
`evaluator`	`string`	Registry ID for the evaluator used
`result`	Unique to each evaluator See “Output” for each evaluator (e.g., for Grade Level Appropriateness)	Detailed internal analysis data specific to each evaluator
`metadata`	`EvaluationMetadata` ↗	Includes model used to generate the evaluation, total evaluation processing time in milliseconds, input tokens, and output tokens

Quickstart

Install the SDK and run your first evaluator.

Configuration

Configure evaluators, including API keys and options.

Error handling

Handle configuration, validation, and API errors.

Batch evaluator

Evaluate a batch of text from a CSV file using Student-Facing Text evaluators.

Understanding evaluators

Getting started

SDK API reference

Student-Facing Text evaluators

Feedback evaluators

Academic standards evaluators

Durable skills evaluators

Datasets

Resources

Inputs

Student-Facing Text

Feedback

Academic Standards

Output

Quickstart

Configuration

Error handling

Batch evaluator

​Inputs

​Student-Facing Text

​Feedback

​Academic Standards

​Output

​Related topics

Quickstart

Configuration

Error handling

Batch evaluator

Inputs

Student-Facing Text

Feedback

Academic Standards

Output

Related topics