Skip to content

Update terminology from scanners to guardrails #222

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
danielcayer wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update terminology from scanners to guardrails #222

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
6 changes: 3 additions & 3 deletions docs/class6/module1/laba/laba.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,11 +6,11 @@ Now that we have an understanding of the F1 score, it is also important to under
For this task, we have the **prompt-evaluator** :ext_link:`https://gitlab.com/Artemouse/prompt-evaluator`,
a lightweight evaluation tool for AI prompts and model responses: it lets you systematically test, score, and compare outputs from large language models against criteria you define. Instead of manually judging whether a model’s reply is good or bad, this tool runs structured evaluations to measure qualities like accuracy, relevance, safety, and adherence to rules (e.g., F5 AI Guardrails). It’s useful for developers and AI teams who want repeatable, automated quality checks as they improve prompts, switch models, or tweak AI behavior.

We will use **prompt-evaluator** with a validation dataset to test our scanners.
We will use **prompt-evaluator** with a validation dataset to test our guardrails.

1. First, we need to ensure that all our prompt injection scanners in the **Test project** are enabled.
1. First, we need to ensure that all our prompt injection guardrails in the **Test project** are enabled.

In the main left tab go to **Projects** ⇒ Click **View** for the **Test project** ⇒ Click on the **Prompt injection package** and make sure that all scanners are enabled.
In the main left tab go to **Projects** ⇒ Click **View** for the **Test project** ⇒ Click on the **Prompt injection package** and make sure that all guardrails are enabled.

2. Go back to the **Test project** and click on **API Tokens** ⇒ **Generate API token** ⇒ Name it **f1testing** and click **Save**

Expand Down