Create an AI interviewer

Create Interviewers that produce high-signal AI interviews, clean scorecards, and fair shortlisting decisions.

The InterviewFlowAI interview is structured and time-boxed (configurable from 10 to 60 minutes), so your Interviewer setup quality directly impacts Candidate experience and scoring quality.

How Interviewer creation works

In the Create Interviewer flow, you configure the Interviewer through 5 specific steps:

• Role details: Role identity, hiring profile, and the role brief.
• Interview settings: Format, timing, required inputs, and Candidate messaging.
• Application form: Maintain screening questions and knockout criteria.
• Question settings: Adjust manual, resume, and skill-based question sources.
• Questions: Review question order and the prompts the AI will use.

1. Role details

   Keep the headline role information precise so the rest of the interviewer setup stays coherent.

   1. Role identity & hiring profile

   • Write a specific Interviewer title: Include clear seniority and function (maximum 255 characters).
     • Better: Senior Frontend Engineer (React)
     • Avoid: Developer
   • Select the closest role: Define the functional role (maximum 255 characters).
   • Experience levels: Add minimum and maximum experience limits when the role requires it.
   • Logistics: Define the interviewerType (full-time, part-time, contract) and locationType (remote, onsite). If onsite, provide the country, city, and zipcode.
   • Benefits: Clearly state the perks and benefits (maximum 5000 characters).

   2. Role brief and context

   • Description: Focus on business outcomes and real responsibilities.
   • Requirements: Separate must-have skills from nice-to-have skills. Keep requirements concrete.
   • Context: You can now provide key details about the role, such as salary, location, or team structure. The AI interviewer will use this information to answer any questions Candidates may have during the interview.

   3. Candidate tags

   Keep filter labels and answer options tied to this Interviewer so Owners and Viewers can compare Candidates quickly. Keep each tag aligned with one Owner/Viewer-facing hiring signal and its allowed values.

   • Tag name: Choose a descriptive name for the tag (e.g., Work Authorization).
   • Options: Type an option and press Enter. Keep values short and standardized so filtering stays clean.
2. Interview settings

   Review the timing, interview format, and required Candidate inputs in one place.

   1. Candidate experience

   • Interview Language: Choose based on the target Candidate pool.
   • Max. Interview Duration: Set the time limit (10 to 60 minutes).
   • Link Expiration: Set link expiration (1 to 10 days).
   • Retakes allowed: Set how many retakes a Candidate can use, from 1 to 3. Candidates can retake the interview until they use the allowed number of attempts.
   • Inputs and restrictions:
     • Video response: Require Candidates to submit a video. Note: this is locked on if resume-based custom questions are enabled.
     • Portfolio: Ask Candidates to include their portfolio link.
     • Desktop restriction: Limit the interview flow strictly to desktop devices.

   2. Intro video

   Upload a short welcome or role overview video for this Interviewer. This will be played before the AI interview begins to give Candidates a more engaging and personalized experience.

   • Accepted formats: MP4, WebM, MOV.
   • Maximum file size: 50MB.

   3. Interview Messages

   Customize the AI interviewer’s messages to Candidates.

   Use variables like {fullName}, {firstName}, {jobTitle}, and {jobRole} to personalize messages. These will be automatically replaced during the interview.

   • Introduction Message: The first message Candidates hear when starting the interview.
     • Default: “Hi , I’ll be your AI interviewer today. It’s a pleasure to meet you! This is a structured interview designed to provide a fair and consistent experience for all candidates. For each question, you’ll have about two minutes to respond. If you don’t understand a question, you can ask me to repeat it. Are you ready to get started?”
   • Ice Breaker (Optional): A friendly opening question to help Candidates feel comfortable.
     • Default: “To start off, could you tell me a little about yourself and what excites you about the role?”
   • Interview Closing Message: The final message Candidates hear at the end of the interview.
     • Default: “Thank you for your time. Our team will review your responses and get back to you soon.”

   4. Post-interview questions

   Add questions Candidates see after the interview is complete. Use these to collect follow-up details that do not need to be part of the AI conversation, such as a code repository link, portfolio URL, take-home assignment link, or final availability details.

3. Application form

   Filter Candidates based on must-have qualifications before they reach the interview. Screening questions appear on the application form and can automatically filter out unqualified Candidates.

   The best screening forms feel precise, not heavy. Short, specific questions outperform long application forms.

   1. Configure screening questions

   You can quickly add pre-built screening questions (e.g., Background Check, Education, Visa Status, Language, etc.) or create your own custom questions.

   For each question, define:

   • Question: The prompt the Candidate will see.
   • Response type: Numeric, Text, or Yes/No.
   • Ideal answer: For Numeric questions, set a minimum value.
   • Required: Toggle whether the Candidate must answer to proceed.
   • Must-have qualification: Mark this setting to automatically reject Candidates who answer incorrectly.

   2. Best practices

   • Target deal-breakers: Reserve Must-have qualification for true deal-breakers only.
   • Calibrate thresholds: Review numeric thresholds (like minimum years of experience) anytime the role seniority changes.
4. Question settings

   Tune sources to match the role structure. Different roles need different blends of structured and personalized interview questions.

   You can mix and match three different question sources to form your overall interview strategy:

   • Manual questions: Keep every interview anchored on the same themes. Pre-written, static questions asked to every Candidate. You will build these in the next step.
   • Resume-based: Helps the interview feel tailored without manual effort. The AI dynamically generates a set number of questions (up to 10) based on the Candidate’s uploaded resume and your specific generationInstructions (maximum 4000 characters).
   • Skills-based: The AI generates relevant questions and scenarios to evaluate specific competencies. You can add one or more skills alongside a common custom instruction to define context and complexity, driving a dynamic 5-minute conversation module.

   Use the final review step to verify order and depth before saving.
5. Questions

   Review the final question flow. This is the best place to confirm the Interviewer still sounds intentional after edits.

   Quality check the interview flow:

   • Put the highest-signal question sections first.
   • Tighten vague wording before you save so evaluation remains consistent.
   • Check generated counts if the interview now needs more or less depth.

   1. Review dynamic questions

   For sources like Resume questions, verify the settings:

   • Max questions: The number of questions generated automatically for each shortlisted Candidate from their resume evidence.
   • Instructions: Verify the specific prompt the AI uses to pull questions.

   2. Add manual questions

   The AI will ask these manual questions during the interview. For each manual question, you must complete the following evaluation criteria framework:

   Component	Purpose	Details & Limits
   Question	The prompt the AI asks the Candidate.	Must be specific and clear.
   Looking for	The specific traits or evidence you want to hear.	Guides the AI’s scoring engine.
   Strong answer (5)	Concrete examples of a top-tier response.	Sets the benchmark for a perfect score.
   Weak answer (1)	Red flags or lack of specific evidence.	Sets the floor for a failing score.
   Weight	Importance level (1 to 10).	1 is informational, 9 to 10 is role-critical.
   Max follow-ups	How many times the AI can dig deeper.	Must be between 0 and 2.

   2. Weight & follow-up guidance

   • Weight 1: Informational only (excluded from overall score).
   • Weight 5 to 8: Core competencies.
   • Weight 9 to 10: Role-critical differentiators.
   • Max follow-up (0): Use for straightforward factual checks.
   • Max follow-up (1 to 2): Use for behavioral, competency, or dynamic resume/skills questions to ensure the AI gets enough evidence without derailing the time limit.

   3. Question-writing formula

   Use this structure to ensure the AI gets the best data:

   1. Ask for a specific past situation.
   2. Ask for actions taken.
   3. Ask for a measurable outcome.

   • Better: “Tell me about a time you improved conversion in a low-performing funnel. What did you change and what metric improved?”
   • Avoid: “How do you think about conversion optimization?“

   4. Interview prompt-aware best practices

   The AI interviewer is programmed for specific behaviors. To align your questions with its logic:

   • Neutrality: The AI stays neutral (no praise).
   • Evidence-based: It will utilize its follow-up allowance (up to 2 times) to request specific evidence when answers are vague.
   • Scoped: Keep each question focused on exactly one competency.

Pre-publish checklist

Before you publish your Interviewer, review the following requirements:

• Interviewer title, role, and logistics (location/type) are specific and accurate.
• Interview duration and link expiration are set correctly.
• Retakes allowed is set to the intended number of attempts.
• Messages (intro, icebreaker, closing) are within character limits.
• Post-interview questions collect only details needed after completion.
• Screening questions are minimal, with must-haves flagged appropriately.
• Question generation strategy (sectionOrder) is clearly defined.
• Dynamic instructions (Resume/Skills) are clear and under the 4000-character limit.
• Every manual interview question has complete evaluation criteria.
• Follow-up limits do not exceed 2 per question.

Common mistakes to avoid

• Vague instructions: Leaving dynamic generation instructions too broad, leading to irrelevant resume or skill questions.
• Excessive duration: Setting a 60-minute interview but only providing 3 questions.
• Over-processing: Giving every question a max follow-up of 2, which can cause the AI to rush the end of the interview.
• Rigid screening: Marking too many items as a mustHaveQualification.