> For the complete documentation index, see [llms.txt](https://examind.gitbook.io/v1/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://examind.gitbook.io/v1/feedback-machines/get-started.md).

# Get Started

Feedback Machines is a system that harnesses leading-edge AI models — such as those from Anthropic, Google, and OpenAI — to auto-grade and provide detailed, criteria-aligned feedback on qualitative student work: essays, memos, case studies, presentations, EXAMIND Simulations, and more.

You configure a **Feedback Machine** by giving it your assignment instructions and a grading rubric — or have one generated for you. It then evaluates each student submission against those criteria, returning both a grade and detailed feedback tied to your criteria.

{% hint style="success" %}
**No rubric yet? You don't need one to start.** Feedback Machines can generate a rubric for you to the highest pedagogical standards. Just direct it on the qualities that matter for your learning outcomes, and it turns them into a complete, criteria-based rubric you can review and adjust.
{% endhint %}

## How you and your students reach it

You — and your students — can use Feedback Machines two ways:

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Using Canvas</strong></td><td>Reach Feedback Machines from your Canvas course — no separate login for students.</td><td><a href="/pages/wyx4RBNBRoXec2v7Agqf">/pages/wyx4RBNBRoXec2v7Agqf</a></td></tr><tr><td><strong>Without Canvas</strong></td><td>Sign in directly at feedbackmachines.com — no LMS required. The quickest way to try it yourself.</td><td><a href="/pages/T4Hhh9X2oIxzxRfWu8z4">/pages/T4Hhh9X2oIxzxRfWu8z4</a></td></tr></tbody></table>

{% hint style="warning" %}
**Feedback Machines is a separate product from the EXAMIND Platform**, with its own setup — configuring one doesn't configure the other. Its only built-in **LMS integration** is **Canvas**; with any other LMS (or none), use **direct login** (see [Without Canvas](/v1/feedback-machines/get-started/without-canvas.md)).
{% endhint %}

## What it can evaluate

Feedback Machines works with any assignment a student can submit as text, `.docx`, or `.pdf`, including:

* Essays and reports
* Business memos and emails
* Letters
* Case studies
* Negotiation preparation documents
* Negotiation reflections
* Presentation decks (as `.pdf`)

Beyond the text itself, Feedback Machines can evaluate **images and visuals inside PDFs**, and **document formatting in `.docx` files** — margins, font types and sizes, footers, footnotes, and the like.

## Two ways to use it

{% tabs %}
{% tab title="Iterative feedback" %}
Students submit a draft and receive immediate pedagogically optimal feedback aligned with your learning objectives, then revise and resubmit. You can track how many drafts each student submits and how their work improves across iterations.

This mode is built for [skill development](/v1/our-approach/why-iterative-feedback-works.md) — the more feedback-and-revision cycles a student goes through, the more their work tends to improve.
{% endtab %}

{% tab title="Auto-grading" %}
Feedback Machines grades qualitative assignments at scale, producing scores and feedback aligned to your criteria. When configured properly, Feedback Machines exceed human-level inter-rater reliability (e.g. 0.9+ on Quadratic Weighted Kappa).

See [Bulk Grading Assist](/v1/feedback-machines/bulk-grading-assist.md) to grade a whole class at once.
{% endtab %}
{% endtabs %}

## Feedback Machines and EXAMIND assessments

Feedback Machines can also **auto-grade Simulation assessments** in the EXAMIND Platform: once a Feedback Machine is linked to a Simulation, it evaluates the student's interaction against your criteria. (The EXAMIND **Essay** assessment type is instructor-graded.)

{% hint style="info" %}
**Linking is handled by EXAMIND for now.** You can build and configure both a Simulation and a Feedback Machine yourself, but connecting the two currently requires us to set it up — just [contact us](mailto:support@examind.io) and we'll link them. See [Simulation Assessments](/v1/examind-platform/build/assessments/assessment-types/simulation-assessments.md).
{% endhint %}

## Next step

[Build a Feedback Machine →](/v1/feedback-machines/build-a-feedback-machine.md)


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://examind.gitbook.io/v1/feedback-machines/get-started.md?ask=<question>
```

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.