Search code, repositories, users, issues, pull requests...

Phantasm offers open-source toolkits that allows you to create human-in-the-loop (HITL) workflows for modern AI agents. Phantasm comes with 3 main components that work together to create a seamless HITL experience:

Phantasm allows you to have an approval layer on top of your AI agents. This means, you're free to use any AI framework or model you see fit. By using Phantasm, you can delay the execution of certain business critical actions by your AI agents until a human approves them.

This is particularly useful in scenarios where the AI agent is not 100% accurate or the cost of making a mistake is high. For example, an AI agent that can automate calendar scheduling. In this case, you can use Phantasm to make sure that the AI agent schedules the right meetings at the right time.

Phantasm can also relay the action parameters to the approvers. This parameters can be modified by the approvers before approving the action. This is useful if there is only a slight mistake in the action parameters that can be corrected by the approvers. This way the action can be approved with some modifications instead of rejected.

Leave a Comment