IntrinsicDecoy Technologies
|
ShieldstralMistral AI
|
|||||
Related Products
|
||||||
About
Craft your own policies beyond standard abuse categories and enforce them in just minutes.
Intrinsic is a platform for building AI agents for user trust. We hook directly into your existing workflows, and gradually help enhance human review with automation safely and seamlessly.
Automate moderation of text, images, videos and reports with a system that gets better with every moderation action.
Manage review queues and escalations easily with fine-grained RBAC permissions.
Make data-driven decisions based on policy performance reports and platform-wide health monitoring.
Access advanced security, AI-powered analytics, and comprehensive information governance.
|
About
Shieldstral is a 3B open-weights, policy-adaptive multimodal safety classifier designed to evaluate text, images, and text-plus-image content using policies defined at inference time. Instead of relying on a fixed taxonomy of harm categories, it frames moderation as a binary question-answering task: users provide an instruction describing the evaluation context and strictness, a yes-or-no safety question, and the content to judge. The model reads the “yes” and “no” logits and converts them into a continuous, calibrated safety score, allowing applications to threshold or rank results by confidence rather than depend on a single discrete label. This formulation unifies prompt classification, response moderation, refusal detection, toxicity detection, and multimodal safety in one interface, while letting teams adapt policies without retraining the model. Shieldstral can evaluate prompts, responses, prompt-response pairs, images, and images with accompanying text.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
Trust and safety teams interested in a powerful AI content moderation and workflow solution
|
Audience
AI platform teams that need customizable, multimodal content moderation without retraining a separate safety model for every policy
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
No information available.
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationDecoy Technologies
United States
withintrinsic.com
|
Company InformationMistral AI
Founded: 2023
France
mistral.ai/news/shieldstral/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
|
|||||
|
|
||||||
Categories |
Categories |
|||||
|
|
|