HyperSkill User's Guide
  • Overview
    • System Requirements
    • Create a HyperSkill Account
    • Quick Start Guide
  • Virtual Entities (VX)
    • Public Virtual Entities
    • Import Virtual Object (VO) from HyperSkill Desktop
    • Edit Virtual Objects
    • VX Publisher
      • Import Model as Virtual Object (VO)
      • Import Model as Virtual Person (VP)
      • Import Model as Virtual Space (VS)
      • Special Considerations
    • Export Model from SolidWorks
    • Export your Virtual Object to a QR Code (Hololens)
    • Special Virtual Objects
      • Train
      • Digital Caliper
      • Blur
      • Crossbow
      • Picture Frame
      • Drone
      • Painting
        • Setup
        • Spray Painting
        • Pen
      • Timer Display
  • Media Upload
  • Authoring a Simulation
    • Object Browser
    • Inspector
      • General
      • Description
      • Grab Mechanics
        • Basic
        • Slider
        • Rotator
        • Dragger
        • Grabber
        • Climbable
      • Customizable
      • Player
    • Scene Layout
      • Asset Movement Tools
      • Skybox
      • Set Spawn Position
      • Show Axis
      • Assets
    • State Machine
      • Scenario Flow
        • State Machine Interface
        • State Actions
        • Attributes
          • Default Attributes
        • Transitions
          • Use
          • Snap
          • Proximity
          • Collide
          • Utterance
          • Use Release
          • Conditions
      • Rules
      • Triggers
        • Collide
        • Conversation Update
        • Grab
        • Proximity
        • Rejected Intent
        • Snap
        • Voice Intent
        • Ungrab
        • Unsnap
        • Use
        • Use Release
        • Wait
      • Conditions
        • Simulation Condition
        • Account Condition / User Attributes
      • Actions
        • How to Author the State Machine
        • Add Feedback Log
        • Add a Follow Camera
        • AI Chat
          • How to Author the Chat Box in a simulation
        • Animation Controller
        • Animation State Transition
        • Camera
        • Change Character Prompt
        • Checklist
        • Display Image
        • Display Message
        • End Timer
        • Go To Sim
        • Highlight
        • IK Solver
        • Leaderboard
        • Lighting Settings
        • Look At
        • Microphone
        • Open Link
        • Particle Controller
        • Play Animation
        • Play Audio
        • Play Video
        • Quiz
        • Reset Chat
        • Rotate
        • Run Agent
        • Set Attribute
        • Show Feedback Log
        • Spatial Audio
        • Spawner
        • Speak
        • Start Timer
        • Switch Virtual Assistant
        • Transition Effect
        • Translate
        • VCode Function
        • Wait
    • Object Groups
    • Paths
    • Wires
      • Wire Builder Interface Description
    • Simulation Settings
      • Experience Settings
        • Microphone
        • Player
        • Documents
        • Virtual Assistant
        • Conversational AI
        • Wires
        • Pin Code Multiplayer Overrides
        • Experts
      • Authoring Settings
        • Desktop
        • VR
    • SimGenie
    • Simulation Templates
    • Save States
  • Experience a Simulation
    • User Interface
    • Controls
    • Multiplayer
  • AI
    • Natural Conversations
    • Large Language Models & Data Privacy
    • AI Chat
      • How to Author AI Chat
      • SimKB
      • Edit Mode
      • Test Mode
    • Agents
      • How to Author an Agent
      • Edit Mode
      • Test Mode
    • PDF Question Answering
    • Review Mode
    • Settings
    • Conversational AI
      • Helpful Terminology for Conversational AI
        • Multi-expert dialog
        • Natural Language Understanding
        • Experts
          • List of experts developed so far
            • HM Graph Expert - Deployed
            • Key Phrase Expert - Deployed
            • Catch All Expert - Deployed
            • Azure PDF Expert - Standalone
            • Gaze Expert - Standalone
            • Knowledge Graph Expert - Standalone
  • Mixed/Augmented Reality
    • Create a Mixed Reality experience
    • Spatial Anchors
  • Publish
    • Playlist
    • LMS Integration
    • Embed Mode
  • Insights and Analytics
    • Logging Attributes
      • Detailed Event Table
      • Detailed Attributes Table
  • Web Portal
    • Simulation / Virtual Object Browser
    • Organizations
    • Settings
  • Subscriptions
  • Skillful
    • FAQ
  • Archived
    • Wires
Powered by GitBook
On this page
  1. AI
  2. Agents

Edit Mode

PreviousHow to Author an AgentNextTest Mode

Last updated 1 year ago

The agents edit tab (AI->Agents) contains options for creating and editing agents for HyperSkill.

By default, the agent settings will be locked until you create or select an agent.

You can edit the following properties of agents:

Property
Description

Name

The name of the agent.

When to run

Determines when the agent should generate a response. The options include "Run after user utterance", "Run through state machine", and "Run after character".

Use History

Determines if the agent should look at the last speech action or the entire conversational history. Generally the agent should look at the entire history.

Language Model

Determines which LLM to use. Azure refers to GPT4, Google refers to Google's Gemini Pro.

Instructions

The instructions the agent is intended to follow.

The options for "When to run" refer to the following:

Option
Description

Run after user utterance

The agent will run after the user says or types something into HyperSkill every time. This is useful for evaluating the user at every dialogue turn.

Run through state machine

Run after character

The agent will run after the chit-chat roleplaying character finishes speaking. This is useful if you want to include the character response in an analysis.

When you click on the "+Add" button under "Describe Your Agent's Output", a new box will be added where you can describe what the agent should update in HyperSkill.

Property
Description

Name of Output

A descriptive name for the LLM to use.

Description of Output

This explains what kind of content the LLM should create. It could be something specific like "a score from 0-100" or more general like "feedback for the learner."

Output Destination

The agent will run only when the is used. This is useful to run the agent only when it is needed.

We feed names and descriptions to a powerful language model, which then uses them to create new content that matches those descriptions. The created content can be automatically stored in a specific area () for you to use easily. You can create as much outputs as you want, but access in HyperSkill might become restricted depending on your subscription plan and usage. You can edit the following fields:

This tells the system where to put the generated content. It's like a specific label on a box where you want the information stored. These dropdowns point to a particular piece of data () for a virtual object.

attribute
state action run agent
attribute
The agents window when editing
An empty output box after clicking on the "+Add" button.