AI Output Details
The AI Output-Details Stage is used to generate a dynamic, AI-powered response based on a custom prompt and input data. This stage is ideal when you want to leverage AI to generate summaries, suggestions or natural language responses, and store the result in a variable for use in later stages.
AI Output-Details
Select variable or repositories:
The dropdown displays the "Variable" value in the list.
Select variable or fields:
The dropdown displays all variable names from previous stages.
If no variables are available from previous stages, it shows 'No variables found’.
When a variable is selected in the first dropdown, the second dropdown dynamically displays all variables from previous stages.
Create a prompt:
“Create a prompt” field is mandatory, the validation message displays as 'Prompt is required' when the prompt field is left empty.
When you copy a variable from the dropdown, it gets inserted into the prompt in the following format:
${Variable:variableName}
After saving the form, the prompt remains exactly as entered — no formatting loss or data corruption occurs when you reopen the stage.
Output Variable
You must define an output variable where the AI response will be stored.
This variable can be used in downstream stages like Send Email, Update Record, or Condition, etc.
Example Scenario:
You want to evaluate how well a candidate matches a job role based on their profile, and store an AI-generated score (0–10) for use in decision-making or filtering.
Use AI Output-Details to analyze the resume and return a numeric score (0–10) based on job match quality.
Prompt:
Based on the following details, generate a candidate score out of 10
Candidate Details:
Candidate Name: Priyal Kumar
Experience: 2.5
Skills: Java, C, C++, HTML
Candidate Specification: Prompt Engineering.
Job Details:
Job Title: Junior Software Developer Experience Required: 2+ years Key Skills: Java, C, C++, HTML Job Description: We are looking for a junior software developer with hands-on experience in Java, C, C++, and HTML. The ideal candidate should have strong programming fundamentals, good problem-solving skills, and the ability to contribute to both front-end and back-end development tasks.
Only return a numeric score without explanation.
Output Variable:
Variable Name: CandidateScore
Store variable output like 7
AI Output-Details Under For Each Stage
Select variable or repositories:
The dropdown list displays the Variable and Repository name selected in the 'For Each' stage.
Select variable or fields:
When a variable value is selected in the first dropdown, the second dropdown dynamically displays the list of available variables from previous stages.
When a repository value is selected in the first dropdown, the second dropdown displays all fields of the selected repository.
If no variables are available from previous stages, the second dropdown displays: "No variables found."
Create a prompt:
“Create a prompt” field is mandatory, the validation message displays as 'Prompt is required' when the prompt field is left empty.
Copied variable value should be pasted into the prompt in following format:
For Variables: Format: ${Variable:variableName} Example: ${Variable:eligibilityStatus}
For Repository Fields: Format: ${RepositoryName:FieldName} Example: ${Candidate_Details:Experience} -The system uses the internal name of the repository and the field when generating the token.
After saving the form, when the stage is reopened, the entered prompt should appear exactly as saved without any formatting changes or data loss.
Scenario: Example
You want to send a personalized email to each candidate from your Candidate Tracker. Before sending, the AI will summarize their profile into 1–2 lines. This summary will be included in the email body.
Example Setup:
Repository: Candidate Tracker
Fields in Repository:
Name
Email
PositionApplied
CandidateSpecification
Skills
Stage: For Each
Repository Selected: Candidate Tracker
Purpose: Loop through each candidate record.
Under For Each → Stage: AI Output-Details Purpose: Summarize the candidate’s profile using AI. Prompt:
Summarize the following candidate profile into 1–2 lines suitable for HR communication: ${CurrentRecord:CandidateSpecification}
Output Variable: CandidateSummary
Under For Each → Stage: Notification (Email) Purpose: Send a personalized email to the candidate using the AI-generated summary.
Message Body:
Dear ${Variable:Name},
Thank you for applying for the ${Variable:PositionApplied} position.
Here’s a quick summary of your profile:
${Variable:CandidateSummary}
Our team is reviewing your profile and will get back to you shortly.
Warm regards,
HR Team
Result
Each candidate receives a unique email with a personalized summary of their profile. The summary is generated automatically using AI, and the process runs for every record in the Candidate Tracker repository.
AI Output Under Condition Stage
Select variable or repositories:
The dropdown shows variable values.
Select variable or fields:
It shows all variables from previous stages in the dropdown.
If no variables are available from previous stages, it displays 'No variables found’.
When a variable value selected in the first dropdown, the second dropdown dynamically shows the list of available variables from previous stages.
Create a prompt:
“Create a prompt” field is mandatory, the validation message displays as 'Prompt is required' when the prompt field is left empty.
When you copy a variable from the dropdown, it gets inserted into the prompt in the following format:
${Variable:variableName}
After saving the form, the prompt remains exactly as entered — no formatting loss or data corruption occurs when you reopen the stage.
Expected Behaviour: AI Output
Scenario
You are screening candidates for a job position. Each candidate is scored based on their resume. You want to trigger an AI-generated message only for candidates who score above 7.
Example Setup
1. Stage: Condition - Logic: If ${Variable:CandidateScore} > 7 - Description: Check if the candidate’s score is above 7.
2. Under Condition → Stage: AI Output-Details - Prompt: Summarize this candidate's strengths in 2 lines. Resume: ${Variable:ResumeSummary} - Output Variable: CandidateSummary - Description: Only executed if score > 7.
3. Stage: Notification - Use the AI-generated summary in an email or notification. - Message:
"Hi ${CurrentRepository:CandidateName}, based on your resume, here’s a summary: ${Variable:CandidateSummary}"
Last updated