Interview Not Counting

If you see an interview in your project but it is not counting toward your usage or appearing in your analysis, it most likely did not meet the quality threshold. This is intentional — Koji's quality gate ensures that only meaningful interviews contribute to your research insights.

---

Why Interviews Do Not Count

Koji assigns a quality score to every completed interview. Interviews that score below a threshold of 3 (on a scale of 1 to 5) are considered low-quality and are excluded from your usage count and aggregate analysis.

This is a feature, not a bug. The quality gate protects your research data from being diluted by interviews where the respondent did not engage meaningfully.

---

What Causes a Low Quality Score

Several factors can result in a quality score below 3:

Minimal Responses

The respondent gave very short, single-word, or one-sentence answers throughout the interview. Meaningful qualitative research requires detailed, thoughtful responses. An interview where every answer is "yes", "no", or "fine" does not provide useful insight.

Off-Topic Responses

The respondent's answers did not relate to the interview topics. This can happen when someone is not genuinely interested in providing feedback and clicks through the interview to complete it quickly.

Insufficient Length

The interview ended very early — either the respondent left after just a few exchanges or was disconnected. A very short interview does not have enough content to generate meaningful analysis.

Gibberish or Spam

The respondent entered random text, keyboard mashing, or repetitive nonsensical content. Koji's quality assessment detects these patterns and scores the interview accordingly.

Copy-Pasted Content

Responses that appear to be copy-pasted from external sources rather than genuine answers to the interview questions.

---

How to Check an Interview's Quality Score

You can view the quality score for any completed interview:

1. Open the interview from your project's interview list.
2. Look for the Quality Score indicator, typically displayed as a numeric score or a visual indicator near the interview header.
3. Interviews below the quality threshold are marked accordingly.

The quality score is also available via the API when you retrieve interview data.

---

What Happens to Low-Quality Interviews

Interviews that do not meet the quality threshold:

• Are not counted toward your plan's interview usage.
• Are excluded from aggregate analysis — they do not influence theme extraction, insight generation, or project-level reports.
• Are still accessible. You can view the transcript and the quality score. Nothing is deleted.
• Can be reviewed. You might find the transcript useful for other purposes even if it did not meet the quality bar.

This means you are never "charged" for a low-quality interview. Your interview credits are preserved for interviews that actually contribute to your research.

---

Improving Interview Quality

If you are seeing a high rate of low-quality interviews, consider these adjustments:

Improve Your Interview Guide

A well-written interview guide elicits better responses. See How the Quality Gate Works for detailed guidance on writing guides that encourage thoughtful answers.

• Ask open-ended questions. Questions that can be answered with "yes" or "no" lead to short responses.
• Provide context. Help respondents understand why their detailed feedback matters.
• Set expectations. Let respondents know upfront that the interview takes a certain amount of time.

Screen Your Respondents

If you are recruiting respondents externally, quality issues may indicate a recruitment problem:

• Use screening criteria. Filter for respondents who have relevant experience with your product or topic.
• Verify engagement. Look for respondent panels or recruitment methods that prioritize quality over volume.
• Set expectations. Tell respondents what the interview involves and how long it takes before they start.

Use the Right Interview Mode

Some respondents express themselves better verbally. If you are seeing short text responses, consider enabling voice mode. Conversely, some respondents prefer typing and may give more detailed written answers.

Check Your Distribution Method

How respondents arrive at the interview matters:

• Personal invitations tend to yield higher quality than anonymous open links.
• Context-specific triggers (like a post-purchase survey) capture respondents when they have relevant recent experience.
• Incentive alignment — make sure any incentives you offer do not inadvertently attract respondents who rush through without engaging.

---

Understanding Quality Scores

The quality score reflects multiple dimensions of the interview:

For a complete breakdown of quality scoring, see Understanding Quality Scores.

---

Edge Cases

The respondent gave great answers but the interview did not count

This can occasionally happen if the interview was very short (only a few exchanges) even if the content was good. The quality gate considers both content quality and conversation length.

An interview counted but I think it should not have

The quality threshold is designed to be fair across a wide range of interview styles. If you believe an interview was incorrectly scored, review the transcript and the quality breakdown. You can manually exclude specific interviews from your analysis if needed.

My test interviews are not counting

Test interviews where you quickly click through with minimal responses are scored the same way as real interviews. If you want to test the full flow, provide genuine, detailed responses.

---

Next Steps

• Learn how the quality gate works in detail
• Understand quality score components