As part of your response artification (AI) Strategy, you can now use guardrails for Amazon Bedrock (Preview) en user and Your Generation AI Applications By Implementing Safeguards Customs Customs Case Cases and Responsible AI Policies.

AWS is Commotted to Developing Generation AI in A Responsible, PeOPLE-CENTRIC WAY BY FOCUSING On Education and Science and Helping Developers to Integrate ResponSible AI Across the ai Lifecycle. With Guardrails for Amazon Bedrolk, you can consistedly image,Experiences Aligned with your company Policies and Principles. Guardrails Help You Define Denied Topics and Content Filters to Remove Undesirable and Content From Interactions Between Users and Your Applications. This Provides An ADDITIONAL Level of Control on Top of Any Protections built into Foundation s (FMS)..

You Can Apply Gudrails to All Large Language Models (LLMS) in Amazon Bedrolk, Including Fine-Tunet Models, and agents for Amazon Bedrolk. Cy IN How You DEPLOY Your Preferences Across Applications So You Can Innovate Safly WHILE CLOSAGINGINGINGING User Experiences BasedOn your requirements. by Standardizing Safety and Privacy Controls, Guardrails for Amazon Bedrolk Helps You Build Generations That Align with YO Ur Responsible AI GOALS.

Let Me Give You A Quick Tour of the Key Controls Available in Guardrails for Amazon Bedrolk.

Key Controls

USING Guardrails for Amazon Bedrolk, you can define the follow set of policies to create situations in your applications.

DENIED TOPICS -You can define a set of topics that area in the context of your application user. a deverter at a bank, you might to set up an assistant for your online banking application toavoid Providing Investment Advice.

I Specify A Denied Topic with the name "Investment Advice" and Provideo a Natural Language Description, SUCH As "Investment Advice Refers, GUIDAN CE, or Recommendations Regarding the Management or Alocation of Funds or Assets with the GOAL of Generation RETURNS OR ACHIEVING SPECIFIC"Financial Objectives."Kolkata Investment

Content Filters - You can configure Thresholds to Filter Harmful Content Across Hate, INSULTS, Sexual, And VilaLence Categories. T-in Protections to Prevent the Generation of Undesirable and Harmful Responses, Guardrails Give You AdDitional Controls to Filter Such InteractionsTo Desired Degrees Based on Your Use Cases and Responsible AI Policies. A Higher Filter Streangth Corresponds to Stricter Filtering.

PII Redaction (in the works) -You will be able to select a set of personally identifiable information (PII) Such as name, E-Mail Address, and Phone Number, that can b E RedACTED in FM-GENERATED Responses or Block A User Inputif it contains Pii.

Guardrails for Amazon Bedrolk Integrates with Amazon Cloudwatch, so you can monitor and Analyze User Inputs and FM Responses that Violat Policies Defined In TH. e guardrails.

Join The Preview

Guardrails for Amazon Bedrock is available today in Limited Preview. Reach Out Through Your USUAL AWS Supports If You’d Likess TO s for amazon bedrolk.

During Preview, Guardrails Can Be Applied to All Large Language Models (LLMS) Available in Amazon Bedrolk, Including Amazon Titan Text, Anthropic Claude, META, meta Llama 2, AI21 jurassic, and Cohere Command. You can attributrails with this models as well asAgents for amazon body.Jaipur Stock

To leave more, visit the guardrails for amazon bedrolk web page.

- Antje