Resource
API Request Variable Builder
Turns a reusable API request prompt into a clean variable set covering endpoint, method, auth, payload, response format, and error handling.
Candidate Evaluation Variable Builder
Documents variables in candidate evaluation prompt templates — candidate name, role, interview notes, strengths, concerns, and recommendation.
Overview
Interview feedback templates are often shared across a hiring panel, with each interviewer filling in different sections. When evaluation templates get adapted per team or interview stage, {{recommendation}} and {{decision}}, or {{strengths}} and {{positives}}, appear as separate names for the same field across different panel versions. When the variable names differ between panelists, synthesising the feedback requires manual alignment. Documenting and aligning the variable set before the template is circulated means every interviewer fills in the same structure, in the same format.
How to use this resource
-
Open in Prompt Variable Builder
Load the evaluation template. The tool detects all eleven variables.
-
Check for similar variable names
Check that recommendation is named consistently across your panel templates. Some templates use {{decision}}, {{verdict}}, or {{hireRecommendation}} — the similarity check will surface those if present alongside each other.
-
Set types and format descriptions
Set interviewDate as date type and recommendation as list (Hire / No hire / Needs review). Add descriptions to strengths and concerns specifying expected detail level.
-
Share the variable reference
Distribute the Markdown export to panelists before the interview week. Use JSON or CSV for HR tool integration.
Why This Works
- {{recommendation}} and {{decision}}, or {{strengths}} and {{positives}}, are the naming pairs most likely to diverge across different interviewers adapting the same template — aligning them before the panel meets prevents manual reconciliation after
- Recommendation is the variable with the most naming variation across evaluation templates — a defined list of accepted values prevents ambiguous hiring signals
- A shared variable reference before interviews start means all panel feedback arrives in the same format, ready for synthesis
Best for
- Hiring panels where multiple interviewers use the same feedback template for the same candidate
- Recruiting processes where interview feedback is fed into an ATS or HR platform automatically
- Teams where inconsistent feedback formats have slowed down hiring decisions in the past
Not for
- Informal one-on-one conversations where structured feedback is not the norm
- Final round debrief meetings where feedback is discussed verbally rather than submitted as structured data
Use cases
- Standardising the evaluation template shared across a hiring panel — catching {{recommendation}} and {{decision}}, or {{strengths}} and {{positives}}, before they diverge across interviewers
- Documenting what each variable expects so panel members fill in strengths and concerns in a consistent format
- Generating a variable schema for an HR tool that aggregates feedback from multiple interviewers
- Exporting a Markdown reference so panelists know the exact format for the recommendation variable
FAQ
How does this catch when panelists use different names for the same evaluation field?
The similarity check surfaces near-duplicate variable names when they appear alongside each other — the drift pairs it targets are {{recommendation}} vs {{decision}} (or {{verdict}}, {{hireRecommendation}}) and {{strengths}} vs {{positives}}. The prompt-variable-builder detects all eleven variables in the evaluation template; aligning names before circulating means every interviewer fills the same structure, ready for synthesis.
How do I constrain the recommendation field so panelists don't write freeform answers?
Set {{recommendation}} as a list type with accepted values Hire / No hire / Needs review, per step 3 — recommendation is the variable with the most naming and value variation, and a defined list reduces ambiguous hiring signals. You'd also set {{interviewDate}} as date type. The builder documents and exports the schema (Markdown, JSON, or CSV); it standardizes the format, it doesn't score candidates.
Where does the exported variable reference go once it's built?
To your panel and tools before interview week. Step 4 distributes the Markdown export to panelists so everyone knows the exact format for each field, and JSON or CSV feeds an ATS or HR platform that aggregates feedback. It defines and documents the variables so submitted feedback arrives consistently; the actual hiring judgment stays with the panel.
More resources from Prompt Variable Builder
Resource
Landing Page Variable Builder
Cleans up variables in landing page prompt templates — headline, audience, pain point, offer, social proof, CTA, and objections.
Resource
User Story Variable Builder
Documents and exports variables from user story and acceptance criteria prompt templates — persona, goal, outcome, constraints, and definition of done.
Resources that pair well
Resource
Agent Task Template
A reusable AI agent task template with variables for objective, context, available tools, constraints, success criteria, failure handling, and output format.
Resource
Agent Instruction Prompt Formatter
Formats fuzzy agent instructions into a structured prompt with objective, available tools, constraints, success criteria, and failure handling.
Related tools
Tool
Prompt Variable Builder
Turn any plain prompt into a reusable, variable-based template — auto-detect values and export.