# Help mark submissions and write feedback

> Help mark submissions and write feedback: 2 companies fully do it, 1 with a limit, 4 carry the tag. Every listing in Learning, tutoring & assessment with the reason and a source.

- Canonical: https://www.anchorterminal.com/niches/learning.mark-and-feedback/
- Markdown: https://www.anchorterminal.com/niches/learning.mark-and-feedback/index.md (~800 tokens)
- Slim: https://www.anchorterminal.com/niches/learning.mark-and-feedback/index.min.md (~230 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/niches/learning.mark-and-feedback/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-15

Two or three companies' docs show a full fit.

| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |
| --- | --- | --- | --- | --- |
| 2 | 1 | 4 | 9 | 3 |

## What counts as done

Each submission's text or files read through the API, draft feedback and a proposed mark per rubric criterion returned to the instructor, and, once approved, grades and comments written back to the gradebook through the API.

How agents ask for it: draft feedback on these essays against the rubric; which submissions are missing; post these grades

## Does the job

The docs show it meets the test above, and nothing we read says otherwise.

- **Instructure Canvas (Instructure, Inc.)**: Submissions return body and attachments with include[] for rubric_assessment, and PUT submissions takes posted_grade, rubric_assessment and comments; acc-16's missing body is a connector gap, not the API.
- **Moodle (Moodle Pty Ltd)**: mod_assign_get_submissions returns submission plugins (online text and files) and mod_assign_save_grade and save_grades write grades and feedback, with mod_assign_list_participants for who is missing.

## Does the job, with a limit

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

- **Learnosity (Learnosity Limited)**: Sessions endpoints list Responses, Response scores, Session Response Feedback and Session Response Score Grading, but only the resource index was read, and every call must be signed with the consumer secret.

- not this job: Kahoot! (Kahoot! AS): No submissions to mark and no grade or comment write; answers are read-only game records.
- not this job: Preply (Preply, Inc.): No submissions or grading endpoints.
- not this job: Quizgecko (Version Zero Limited): No submissions, rubric or grade endpoints.

## What stops agents finishing

- submissions list omits the body
- handwritten or file submissions need separate extraction
- grades written without instructor review

## Around it

Before: learning.coursework-status. After: human-in-the-loop.approve-grades.

## Where this comes from

Weight 9 of 100 in Learning, tutoring & assessment: 3 of 32 accounts (one submissions API gap, one TA's grading tool, one complaint about AI-graded work)

As data: https://www.anchorterminal.com/api/v1/use-cases/learning.mark-and-feedback.json, or the MCP tool get_use_case with id learning.mark-and-feedback. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
