Skip to content

Add CAPTCHA protection docs for assistant #5233

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mintlify wants to merge 1 commit into
base: main
Choose a base branch
from
+12 −0
Open

Add CAPTCHA protection docs for assistant #5233

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions ai/assistant.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,6 +101,18 @@
<img src="/images/assistant/search-suggestions-dark.png" alt="The search suggestions panel in the dashboard with contextual starter questions enabled." className="hidden dark:block" />
</Frame>

### Enable CAPTCHA protection

Check warning on line 104 in ai/assistant.mdx

View check run for this annotation

Mintlify / Mintlify Validation (mintlify) - vale-spellcheck

ai/assistant.mdx#L104 

'Enable CAPTCHA protection' should use sentence-style capitalization.

Protect the assistant from automated abuse by enabling CAPTCHA verification. When enabled, users must pass a CAPTCHA challenge before sending messages to the assistant.

Toggle CAPTCHA protection in the assistant settings on the [Assistant](https://dashboard.mintlify.com/products/assistant) page of your dashboard.

When CAPTCHA is enabled:

Check warning on line 110 in ai/assistant.mdx

View check run for this annotation

Mintlify / Mintlify Validation (mintlify) - vale-spellcheck

ai/assistant.mdx#L110 

In general, use active voice instead of passive voice ('is enabled').

- Users are prompted with a CAPTCHA challenge before their first assistant interaction.

Check warning on line 112 in ai/assistant.mdx

View check run for this annotation

Mintlify / Mintlify Validation (mintlify) - vale-spellcheck

ai/assistant.mdx#L112 

In general, use active voice instead of passive voice ('are prompted').
- After passing the challenge, users receive a short-lived trust token so they are not challenged again on subsequent messages.
- Automated or bot-driven requests that cannot complete the challenge are blocked.

Check warning on line 114 in ai/assistant.mdx

View check run for this annotation

Mintlify / Mintlify Validation (mintlify) - vale-spellcheck

ai/assistant.mdx#L114 

In general, use active voice instead of passive voice ('are blocked').

## Customize assistant behavior

Add a `.mintlify/Assistant.md` file at the root of your documentation project to give the assistant custom instructions that shape how it responds (`Assistant.md` is also an accepted filename). The assistant uses these instructions as system-level context for every response.
Expand Down
Loading