> For the complete documentation index, see [llms.txt](https://help.metaforms.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.metaforms.ai/open-end-cleaning-and-coding/open-end-cleaning/quality-checks.md).

# Quality checks

Metaforms currently runs 14 checks:

1. **Too Short:** the response is too short to carry useful meaning.
2. **Question Echo:** the response only repeats or paraphrases the question.
3. **Cross-Q Duplicate:** the same respondent used identical text for different questions where it does not meaningfully fit.
4. **Cross-Q Similarity:** the same respondent used near-identical text across different questions.
5. **Non-Response:** the answer is an explicit refusal or non-answer, such as “n/a” or “don't know,” when substantive content was required.
6. **Profanity:** the answer contains profane, abusive, hateful, or sexually offensive language.
7. **AI Generated:** the response appears machine-written rather than typed by a respondent.
8. **Off-Topic:** the response is unrelated to both the question and the research objective.
9. **Copy-Paste:** the answer resembles copied marketing text, web content, or boilerplate rather than a personal response.
10. **Gibberish:** the answer contains random characters, punctuation spam, or emoji-only content.
11. **Language Mismatch:** the answer is written in a language other than the survey language and is routed through translation.
12. **PII:** the answer contains personally identifiable information, such as a person's name, phone number, email address, street address, or account number.
13. **Inconsistency:** the respondent's answers contradict each other across questions.
14. **Cross-Respondent Duplicate:** identical or near-identical text appears across different respondents and may indicate copied or coordinated responses.

> **PII note:** The current check flags PII for review; it does not automatically redact the text.


---

# 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, and the optional `goal` query parameter:

```
GET https://help.metaforms.ai/open-end-cleaning-and-coding/open-end-cleaning/quality-checks.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.