Safety Agent for evaluating TutorBot AI responses
Project description
TutorBot Safety Agent
A deterministic, non-autonomous Safety Agent used to evaluate AI-generated responses before they are shown to students.
Purpose
The Safety Agent provides a single, enforceable decision point for:
- Allowing safe responses
- Rewriting risky responses
- Blocking unsafe responses
This package is framework-agnostic and can be reused or extracted into a standalone service in the future.
Public API
from tutorbot_safety_agent import (
SafetyAgent,
DummySafetyAgent,
SafetyDecision,
DecisionType,
)
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file tutorbot_safety_agent-0.1.3.tar.gz.
File metadata
- Download URL: tutorbot_safety_agent-0.1.3.tar.gz
- Upload date:
- Size: 18.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c50f0939720566216b8bd7931f43ad0fffc72cf55d4c757d6dc9abe66f54a2f4
|
|
| MD5 |
d46ad185b47b271881bd4c47358e9df3
|
|
| BLAKE2b-256 |
92c0cb1d498b0a583fc969d587de2c2556cff94f5e2f737bd30e15055a568027
|
File details
Details for the file tutorbot_safety_agent-0.1.3-py3-none-any.whl.
File metadata
- Download URL: tutorbot_safety_agent-0.1.3-py3-none-any.whl
- Upload date:
- Size: 30.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bf9382e144a17879f58a72bedf0b4de566f3c48bfd17844436d10ca7c1917094
|
|
| MD5 |
93966b3e77f0538282f264aba13aab1f
|
|
| BLAKE2b-256 |
a690cade319dc42d9871b8337039d41a83896fafeeab2cab2ce9d65249823a43
|
