# Safety

iframe
## Description

The Safety panel lets you define two layers of content filtering—**Moderation** and **Safety prompts**—to keep mentorAI conversations compliant and appropriate. By screening both incoming learner questions and outgoing AI responses, you protect students, meet institutional policies, and reduce the risk of harmful or off‑topic exchanges.

![](/assets/safety.9df19b454b3e4b0e499a837d473a010cb17742370ca7b95cc1fbd025ed1dfc0d.9c1bb791.png)

## Target Audience

**Instructor**

## Features

#### Dual‑Layer Filtering

- **Moderation Prompt** – scans learner messages before they reach the AI (fast, proactive)
- **Safety Prompt** – scans the AI’s draft response before it’s delivered (second‑layer protection)


#### Customizable Criteria & Messages

Define what counts as disallowed content and what warning text the learner sees.

#### Real‑Time Enforcement

Blocking or redirection happens instantly, preventing inappropriate exchanges from ever appearing in chat.

#### Institutional Tone Alignment

Tailor warning messages to match campus language, policies, or brand voice.

## How to Use (step by step)

#### Open the Safety Tab

- Click the **mentor’s name** in the header
- Select **Safety**


#### Configure the Moderation Prompt

- Acts on **learner messages**
- Enter criteria (e.g., requests for cheating, hate speech) in the text box
- Write the warning learners will see if blocked


**Example message:**

> Please keep the conversation within the bounds of the platform rules.


#### Configure the Safety Prompt

- Acts on the **AI’s response**
- Enter criteria for disallowed content in answers
- Write the fallback message shown if the response is blocked


**Example message:**

> Sorry, the AI model generated an inappropriate response. Kindly try a different prompt.


#### Save Changes

- Click **Save** (top‑right) to apply both prompts immediately


#### Test the Filters

- In a learner chat, enter a prohibited question like:
> How can I cheat on my exam without my professor knowing?
- The **Moderation Prompt** should block the message and display your custom warning


#### Monitor & Adjust

- Periodically review **chat History** for false positives or missed content
- Refine criteria or messages to **tighten or relax** the filter as needed


## Pedagogical Use Cases

#### Academic Integrity Enforcement

Block requests for cheating strategies and direct students toward legitimate study resources.

#### Policy Compliance

Prevent the AI from discussing restricted topics (e.g., medical or legal advice) beyond approved guidelines.

#### Safe Learning Environment

Filter out hate speech, harassment, or explicit content to protect student well‑being.

#### Age‑Appropriate Content Control

Adjust prompts for **K‑12 deployments**, ensuring conversations stay developmentally suitable.

#### Institutional Branding

Use customized warning text that reflects **school tone**—formal, friendly, or supportive—so messages feel on brand.

With **Moderation** and **Safety prompts** properly configured, mentorAI **blocks harmful questions before they reach the AI** and **prevents unsuitable responses from ever reaching learners**—maintaining a safe, compliant, and trustworthy learning environment.