Tutor_Mark

1. Description

This Agent Action provides the Agentforce Tutor with the ability to retrieve the following graded assessment data for a particular student:

• Overall mark.

• Overall feedback.

• Overall pedagogy-aligned instructional feedback.

• Overall pedagogy-aligned instructional feedback to improve by one grade.

2. Reference Action

Apex Class: Tutor_Mark.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_Mark

Agent Action Instructions

Your job is to retrieve the student's overall mark and feedback for a formative assessment. You must follow the below order when using this action:

• Start by obtaining the assessment name from the student.

• Next proceed by obtaining the email address from the student.

• Then run the 'Tutor_Mark' Action by passing in the assessmentName and contactEmail.

• Then return back ONLY the mark and markReason. Follow this up by asking if the student wants to see their instructional feedback to improve their learning journey.

• If yes, return the markPersonalInstruction if it's not empty, else return the markInstruction. Follow this up by asking if the student want to see how to improve their mark by 1 criterion in the rubric.

• If yes, return the markPersonalInstructionPlus1 if it's not empty, else return the markInstructionPlus1. Then finish this Action.

Inputs

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

• Instructions: The name of the assessment. Pass in the exact assessment name as received by the student into the 'Tutor_Mark' Action.

• Advanced Settings:

  • Require input: Enable this setting

  • Collect data from user: Enable this setting

2. contactEmail (Label: Email of the Contact)

• Instructions: The email address of the student. Pass in the exact email address as received by the student into the 'Tutor_Mark' Action.

• Advanced Settings:

  • Require input: Enable this setting

  • Collect data from user: Enable this setting

Outputs

1. mark (Label: Mark)

• Instructions:

  • ALWAYS return the 'Mark' in your first response.

  • You must ALWAYS format your response as: 'Your overall score on the {assessmentName - in bold} assessment was: {Mark - in bold}.

  • The 'assessmentName' and 'Mark' injects should be in bold.

  • The 'Mark' should be a rounded number with no decimal places.

• Advanced Settings:

  • Filter from agent action: Disable

  • Show in conversation: Enable this setting

  • Output Rendering: Rich Text

2. markInstruction (Label: Mark Instruction)

• Instructions:

  • NEVER show this output initially.

  • ONLY show this output if the student replies 'Yes' (or similar) to the question - 'Would you like to see your instructional feedback?' AND if the 'Mark Instruction Personal' output is empty.

  • You must ALWAYS format your response as: 'Your overall instructional feedback is: {Mark Instruction - in italic}.

  • ALWAYS follow up the 'Mark Instruction' output by asking: 'Would you like to see how to improve your mark by 1?'. Format this in bold.

  • There should ALWAYS be a new paragraph between 'Mark Instruction' and the follow up question.

• Advanced Settings:

  • Filter from agent action: Disable

  • Show in conversation: Enable this setting

  • Output Rendering: Rich Text

3. markInstructionPlus1 (Label: Mark Instruction Plus 1)

• Instructions:

  • NEVER show this output initially.

  • You must ALWAYS format your response as: 'To improve by one grade: {Mark Instruction Plus 1 - in italic}.

  • ONLY show this output if the student replies 'Yes' (or similar) to the question - 'Would you like to see how to improve your mark by 1 criterion in the rubric?' AND if the 'Mark Personal Instruction Plus 1' output is empty.

• Advanced Settings:

  • Filter from agent action: Disable

  • Show in conversation: Enable this setting

  • Output Rendering: Rich Text

4. markPersonalInstruction (Label: Mark Personal Instruction)

• Instructions:

  • NEVER show this output initially.

  • ONLY show this output if the student replies 'Yes' (or similar) to the question - 'Would you like to see your instructional feedback?'

  • If this output is empty, use the 'Mark Instruction' as output.

  • You must ALWAYS format your response as: 'Your overall instructional feedback is: {Mark Personal Instruction - in italic}.

  • ALWAYS follow up the 'Mark Personal Instruction' output by asking: 'Would you like to see how to improve your mark by 1?'. Format this in bold.

  • There should ALWAYS be a new paragraph between 'Mark Personal Instruction' and the follow up question.

• Advanced Settings:

  • Filter from agent action: Disable

  • Show in conversation: Enable this setting

  • Output Rendering: Rich Text

5. markPersonalInstructionPlus1 (Label: Mark Personal Instruction Plus 1)

• Instructions:

  • NEVER show this output initially.

  • ONLY show this output if the student replies 'Yes' (or similar) to the question - 'Would you like to see how to improve your mark by 1 criterion in the rubric?'

  • You must ALWAYS format your response as: 'To improve by one grade: {Mark Personal Instruction Plus 1 - in italic}.

  • If this output is empty, use the 'Mark Instruction Plus 1' as output.

• Advanced Settings:

  • Filter from agent action: Disable

  • Show in conversation: Enable this setting

  • Output Rendering: Rich Text

6. markReason (Label: Mark Reason)

• Instructions:

  • ALWAYS return the 'Mark Reason' in your first response after the 'Mark'.

  • You must ALWAYS format your response as: 'Your overall feedback is: {Mark Reason - in italic}.

  • ALWAYS follow up the 'Mark Reason' by asking: 'Would you like to see your instructional feedback?'. Format this in bold.

  • There should ALWAYS be a new paragraph between 'Mark', 'Mark Reason', and the follow up question.

• Advanced Settings:

  • Filter from agent action: Disable

  • Show in conversation: Enable this setting

  • Output Rendering: Rich Text

7. message (Label: Result message)

• Instructions: Result message

• Advanced Settings:

  • Filter from agent action: Enable this setting

  • Show in conversation: Disable

  • Output Rendering: Text