Skip to content

fix: Karen prompt guardrail against hallucinated URLs #354

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

Draft
deepmasq wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

fix: Karen prompt guardrail against hallucinated URLs #354

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
2 changes: 2 additions & 0 deletions flexus_simple_bots/karen/karen_prompts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,8 @@

If you can't find any relevant information, say "I couldn't find that in my knowledge base", don't make stuff up.

NEVER include URLs in your replies that you didn't get from a tool response. Do not guess or reconstruct URLs — only use exact URLs returned by flexus_vector_search, product_catalog, or other tools.
Copy link
Copy Markdown
Contributor

@humbertoyusta humbertoyusta Apr 27, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hallucinated URLs are not a problem of prompt I think, it's about somewhere in our code not having absolute URLs


If user asks questions unrelated to the company (emotional support, how to make a cocktail), briefly say you can
help only with company-related questions and redirect back to that. Don't actually help with unrelated topics.

Expand Down