DostKrita.ai
|
ShieldstralMistral AI
|
|||||
Related Products
|
||||||
About
Create bias-free workplace customer care marketing messages. Dost detects toxicity, microaggressions, and unconscious bias in text, images & videos and nudges the sender to course correct. We have created a bunch of assets that can guide you in change management, communications, and the rollout of Dost. This presentation provides a rollout strategy and plans for launching Dost. This document guides the change owner on the steps they can take to launch Dost across their workspace. This presentation has all the data you will need to build a case for Dost. Use this document for all your stakeholder and employee presentations. Dost is powered by a trained AI model(s) to detect noninclusive language. We rely on established research to define criteria for what constitutes noninclusive language in workplace communications. The training data we use to train our AI models are collected through primary and secondary research.
|
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
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Audience
Businesses searching for a solution to create inclusive messages marketing messages
|
Audience
AI platform teams that need customizable, multimodal content moderation without retraining a separate safety model for every policy
|
|||||
Support
Phone Support
Supported
24/7 Live Support
Not Supported
Online
Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
API
Offers API
Supported
|
API
Offers API
Not Supported
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Supported
|
Training
Documentation
Supported
Webinars
Supported
Live Online
Supported
In Person
Not Supported
|
|||||
Company InformationKrita.ai
Founded: 2020
United States
krita.ai/dost/
|
Company InformationMistral AI
Founded: 2023
France
mistral.ai/news/shieldstral/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Krita.ai
Supported
Lever
Supported
Microsoft Teams
Supported
Mistral AI
Not Supported
Slack
Supported
|
Integrations
Krita.ai
Not Supported
Lever
Not Supported
Microsoft Teams
Not Supported
Mistral AI
Supported
Slack
Not Supported
|
|||||
|
|
|