Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Eliminate your backlog and enhance accuracy in Trust and Safety actions through automation—no engineering, machine learning expertise, or vendor coordination needed. Clearly outline your platform's acceptable content and our AI agents will implement those guidelines with unmatched speed and accuracy. With our quality monitoring solutions, you can confidently apply consistent policies that are easily repeatable. Traditional machine learning models often come with high costs for labeling and training, while training human reviewers can take even more time. Our system allows for the immediate implementation of new enforcement measures without the need for retraining agents or models. Unlike typical ML classifiers, which often lack transparency in their decision-making process, SafetyKit offers comprehensive explanations for every choice made, ensuring you understand the reasoning behind each action. This transparency not only builds trust but also enhances your ability to manage safety effectively.
Description
Shieldstral is an innovative multimodal safety classifier with a 3B parameter open-weight structure, adept at assessing text, images, and combined text-plus-image content based on dynamically defined policies during inference. Rather than adhering to a static set of harm categories, it approaches moderation as a binary question-and-answer format: users submit a contextual instruction outlining the evaluation criteria and strictness, pose a yes-or-no safety inquiry, and present the content for assessment. The model processes the “yes” and “no” logits to generate a continuous, calibrated safety score, enabling applications to prioritize or rank outcomes based on confidence levels instead of relying on a single categorical label. This design effectively integrates prompt classification, response moderation, refusal detection, toxicity assessment, and multimodal safety evaluation into a singular interface, empowering teams to modify policies without the need for model retraining. Shieldstral's versatility allows it to analyze prompts, responses, pairs of prompts and responses, images, and images paired with text, making it a comprehensive tool for safety evaluation. As such, it represents a significant advancement in the field of content moderation.
API Access
Has API
No
API Access
Has API
No
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
No
Webinars
No
Live Training (Online)
Yes
In Person
No
Types of Training
Training Docs
Yes
Webinars
Yes
Live Training (Online)
Yes
In Person
No
Vendor Details
Company Name
SafetyKit
Website
www.getsafetykit.com
Vendor Details
Company Name
Mistral AI
Founded
2023
Country
France
Website
mistral.ai/news/shieldstral/
Product Features
Content Moderation
Artificial Intelligence
No
Audio Moderation
No
Brand Moderation
No
Comment Moderation
No
Customizable Filters
No
Image Moderation
No
Moderation by Humans
No
Reporting / Analytics
No
Social Media Moderation
No
User-Generated Content (UGC) Moderation
No
Video Moderation
No
Product Features
Content Moderation
Artificial Intelligence
No
Audio Moderation
No
Brand Moderation
No
Comment Moderation
No
Customizable Filters
No
Image Moderation
No
Moderation by Humans
No
Reporting / Analytics
No
Social Media Moderation
No
User-Generated Content (UGC) Moderation
No
Video Moderation
No