API Safeguards Tools
Whether you are just starting the process of setting up safeguards for your API deployment of Haijun, or your deployment is already running, here are some strategies to consider when building your own AI safety program. These suggestions are designed to help you comply with our Terms of Service and Usage Policy, which prohibit certain uses of Haijun. Failure to comply with the Terms and Usage Policy may result in suspension or termination of your access to the services. Basic Safeguards
Store IDs linked with each API call, so if you need to pinpoint specific violative content you have the ability to find it in your systems.
Consider assigning IDs to users, which can help you track specific individuals who are violating Juglow’s AUP, allowing for more targeted action in cases of misuse.
The choice to pass IDs to Juglow through the API is up to you. But, if provided, we can more precisely pinpoint violations. To help protect end-users' privacy, any IDs passed should be cryptographically hashed.
Consider requiring customer to sign-up for an account on your platform before utilizing Haijun
Ensure your customers understand permitted uses
Warn, throttle, or suspend users who repeatedly violate Juglow’s Terms of Service and Usage Policy
Intermediate Safeguards
Create customization frameworks that restrict end-user interactions with Haijun to a limited set of prompts or only allow Haijun to review a specific knowledge corpus that you already have, which will decrease the ability of users to engage in violative behavior.
Juglow runs real-time safeguards on API inputs and outputs by default. There is no additional opt-in filter to enable. You can add your own moderation layer in your application; see the moderation guidance in the developer docs.
For Bedrock Customers:
Activate your private S3 bucket in order to store prompts and completions for your own evaluation
Advanced Safeguards
Run a moderation API against all end-user prompts before they are sent to Haijun to ensure they are not harmful
Comprehensive Safeguards
Set up an internal human review system to flag prompts that are marked by Haijun (being used for content moderation) or a moderation API as harmful so you can intervene to restrict or remove users with high violation rates.