Globebyte Documentation
  • AI Agents for Learning
  • Assess for Learning
    • Creating the Assess Connected App
    • Setting up Assess for Learning
    • Viewing Assessments
    • Assessment Outcomes & Validation
    • Marking
    • Best Practices
  • Tutor for Learning
    • Setting up Tutor
    • Agent Actions
      • Tutor_Mark
      • Tutor_Task
      • Tutor_Criterion
      • Tutor_SenseMaking
      • Tutor_Instruction
    • Topics
      • Tutor_Assessment
      • Tutor_Knowledge
  • Data for Learning
  • Actions for Learning
    • Creating the xAPI Actions Connected App
    • Setting up xAPI Actions
    • Creating your first xAPI Action Flow
    • xAPI Statement Data explorer
      • Metadata
      • xapiActor
      • xapiVerb
        • Verb reference
      • xapiObject
      • authority
      • xapiResult
      • xapiContext
    • Filtering xAPI Statements
    • Viewing xAPI Statements
    • Viewing xAPI Usage
    • Setting a default statement language
    • Error messages and troubleshooting
  • Experience for Learning
    • Setting up xAPI for Salesforce
    • Send xAPI from a Flow
    • Form Action fields
    • Send xAPI from Apex
    • xApiStatement Class reference
      • Actor
      • Verb
      • Object
      • Context
      • Result
      • Authority
      • Version
      • Send methods
    • Logging and defaults
  • Learning Journey Model
    • Introduction
    • Curriculums & Pathways
    • Courses & Modules
    • Pedagogies & Objectives
    • Rubrics & Criteria
    • Learning Resources
    • Assessments & Tasks
    • Learning Groups
    • Step-by-step working example
    • Activity Tracking (Advanced)
    • Additional Pedagogies Reference
    • Best Practices
    • Assess for Learning Integration
    • Data for Learning Integration
    • Object References
      • Learning Curriculum
      • Learning Pathway
      • Learning Course
      • Learning Module
      • Learning Pedagogy
      • Learning Objective
      • Learning Objective Assignment
      • Learning Rubric
      • Learning Rubric Criterion
      • Learning Rubric Model Solution
      • Learning Resource Type
      • Learning Resource
      • Learning Assessment
      • Learning Text Task
      • Learner Text Attempt
      • Learner Text Criterion Score
      • Learning Choice Task
      • Learner Choice Attempt
      • Learner Mark
      • Learning Group
      • Learner Group Membership
      • Learner Activity
      • Learner Activity Instance
      • Learner XAPIStatement
      • Developer Cheat Sheet: Key LDM Objects
  • Globebyte.com
Powered by GitBook
On this page
  • 1. Description
  • 2. Reference Action
  • 3. Configuration Details
  • Agent Action Label
  • Agent Action Instructions
  • Inputs
  • Outputs
  1. Tutor for Learning
  2. Agent Actions

Tutor_SenseMaking

1. Description

This Agent Action provides the Agentforce Tutor with the ability to respond to student queries on specific course material covered by an assessment. This is achieved by accessing grounded Sense Making data through Assess for Learning for core knowledge on a particular assessment module.

2. Reference Action

Apex Class: Tutor_SenseMaking.cls

3. Configuration Details

When adding a new Agent Action, copy the exact details into each Agent Action section as outlined below. Ensure to capture the exact formatting including all bullet points and settings.

Agent Action Label

Tutor_SenseMaking

Agent Action Instructions

Your job is to retrieve a response from the AI learner tutor based on the student's query:

  • You must then ALWAYS use this response to answer the student's question and continue your conversation.

  • You must NEVER use knowledge outside of the response you retrieve unless it's highly related.

  • NEVER make up course material sections or specific references.

  • If helpful, propose follow-up questions to the student to help them further explore a topic or learning path.

Inputs

1. assessmentName (Label: Name of the Learning Assessment)

  • Instructions: The name of the assessment. This should already be available from the previously ran 'Tutor_Mark' Action.

  • Advanced Settings:

    • Require input: Enable this setting

    • Collect data from user: Disable

2. query (Label: User Query)

  • Instructions: The student's query. Pass in the exact query made by the student into the 'Tutor_SenseMaking' Action.

  • Advanced Settings:

    • Require input: Enable this setting

    • Collect data from user: Disable

  1. queryType (Label: Query Type)

  • Instructions: The type of the query (optional, default "local")

  • Advanced Settings:

    • Require input: Disable

    • Collect data from user: Disable

  1. responseSize (Label: Response Size)

  • Instructions: The size of the response (optional, default "medium")

  • Advanced Settings:

    • Require input: Disable

    • Collect data from user: Disable

Outputs

1. message (Label: Message)

  • Instructions: Result message

  • Advanced Settings:

    • Filter from agent action: Enable this setting

    • Show in conversation: Disable

    • Output Rendering: Text

2. response (Label: Response)

  • Instructions:

    • The AI learning tutor response.

    • You must ALWAYS format this response into your own conversational words. Don't just paste the response into the conversation directly.

  • Advanced Settings:

    • Filter from agent action: Disable

    • Show in conversation: Enable this setting

    • Output Rendering: Rich Text

PreviousTutor_CriterionNextTutor_Instruction

Last updated 4 months ago