> For the complete documentation index, see [llms.txt](https://docs.siminsights.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.siminsights.com/hyperskill-studio-authoring/ai-features/agents.md).

# Agents

## Overview

Agents add a powerful layer of interactivity to your VR/AR/Web/Desktop learning experiences. These pages explain what they do and how to author them.

## What can Agents do?

Powered by advanced AI (GPT-4 & Gemini Pro), agents can act as intelligent observers within your simulations, providing learners with real-time feedback and guidance.

* **Analyze Learner Performance:** Agents can observe learner speech interactions within the simulation and provide personalized feedback based on their choices.
* **Deliver Dynamic Scores:** Agents can assess learner performance and assign scores based on author-defined criteria.
* **Modify Simulation Attributes:** Agents can dynamically change attributes of virtual objects in your simulation based on learner performance or choices. Imagine an agent ending a simulation early if a learner makes a critical mistake or an agent giving crucial immediate feedback for a learner performing poorly.

## Who has access to Agents?

Availability of Agents depends on your HyperSkill account tier. Refer to your plan details or contact HyperSkill support for more information. You can also email <info@siminsights.com> to ask about getting access.

## In this section

* [How to Author an Agent](/hyperskill-studio-authoring/ai-features/agents/how-to-author-an-agent.md): a step-by-step tutorial that builds a scoring agent.
* [Edit Mode](/hyperskill-studio-authoring/ai-features/agents/edit-mode.md): the agent properties you can edit.
* [Test Mode](/hyperskill-studio-authoring/ai-features/agents/test-mode.md): review a test run of an agent.