See Best practices guide for launching AI-Moderated Interviews and AI/ML data collection projects or the Ensuring Data Quality in AIMI Studies articles for more information.
Before launching your project, please make sure you have considered the following:
The study flow and respondent journey
Realistic expectations for LOI and IR
Actual, not perceived, respondent effort and time
By considering the above points, it will be simpler to address the common challenge of projects being designed based on intended respondent experience rather than actual respondent behavior.
Without appropriate consideration, high drop-off rates, low survey conversion rates, and inconsistent or low-quality data may occur and extend fielding time.
We recommend that you test your project before going live to identify and resolve any issues to ensure a seamless launch.
Learn more about finding the appropriate LOI and IR in our FAQs.
Designing for respondent effort
The most important concept in AIMI projects is that effort, not length of interview, drives performance and data quality.
Effort increases significantly across different modalities:
Text: lowest friction, highest number of completes
Audio: moderate effort, lower conversion
Video: highest effort, highest drop-off rate
This applies to all customers leveraging AI capabilities for research, albeit differently:
Brands and research agencies: Impact on feasibility and cost
AI/ML companies: Impact on data richness vs scale trade-off
We recommend that you inform participants early on about the modality of research that they will participate in and the level of engagement expected. This will enable them to make an informed decision on whether to participate, helping to reduce the drop-off rate and ensuring high-quality responses are submitted.
Curating a rewarding respondent experience
In some AIMI projects, respondents may be asked to:
Open a new tab or window to record audio/video
Use an external tool outside the survey
Leave the survey and return later to complete it
While these setups can work, they often introduce friction in the experience. With each additional step, especially leaving the survey, there is an impact on the volume and quality of responses received. For example:
An interruption to the respondent’s flow can contribute to loss of focus
Introduce confusion about the next steps and lead to a drop-off
This is particularly important for tasks like audio and video, where effort is already higher. Wherever possible, keeping the entire experience within a single, continuous flow (in the same window) tends to result in a smoother experience and stronger completion rates.
A simpler, more seamless experience helps to ensure that:
Respondents remain engaged
Reduce complexity to decrease drop-offs
Improve the overall quality of data and project performance
Pro tip: Use a progress bar to keep respondents engaged
One of the biggest reasons respondents abandon longer qualitative interviews is uncertainty.
When participants don't know how much time is left to complete the survey, they tend to perceive the interview as longer than it actually is. A simple, accurate progress indicator helps set expectations and gives respondents confidence that they're making steady progress.
A progress bar can help:
Reduce perceived interview length
Give respondents a sense of accomplishment as they move through the interview
Reduce anxiety around "How much longer is this?"
Encourage participants to stay engaged until completion
Potentially lower dropout rates, particularly in longer AI-moderated interviews.
Best practices
Set expectations upfront.
Before the interview begins, tell respondents approximately:
how long it will take,
whether audio or video responses are expected,
and that they'll be able to track their progress throughout.
Clear expectations reduce uncertainty from the outset.
Always show progress.
Display a progress bar throughout the interview so respondents always know where they are.Examples include:
Completion percentages e.g., 25% complete
Questions completed: e.g., Question 5 of 12
Time-bound tracker e.g. 8 minutes remaining (only if a reliable estimate is shown)
Ensure accurate progress tracking
Avoid progress bars that stay at 10% for several minutes and then suddenly jump to 90%. Respondents notice when progress feels misleading, which can reduce trust.The progress indicator should reflect genuine advancement through the interview.
Divide the interview into individual stages
Instead of showing one long interview, divide it into logical sections.
For example:
Introduction
Getting to know you
Product experience
Deeper discussion
Final thoughts
Respondents feel they're completing meaningful milestones rather than facing one continuous task.
Celebrate milestones
Small messages throughout the interview can reinforce progress.
For example:
✅ You're about one-third of the way through.
🎉 Great! Halfway there.
👍 Just a few more questions to go.
These simple cues can help maintain motivation.
Don't let the last 10% drag on
One of the biggest user experience frustrations is reaching "90%" and then spending several more minutes finishing. Aim for progress that feels consistent from start to finish with every question so respondents remain engaged with every question.
AI Probing Best Practices
To create a high-quality respondent experience while maintaining interview efficiency, AI probing should be purposeful, limited, and adaptive.
Set maximum number of probes: Configure a maximum number of follow-up probes for each question to prevent repetitive or excessively long conversations.
Add moderation guardrails: Advance to the next question once the maximum probe limit is reached. If a participant cannot provide meaningful input after the designated number of follow-up queries, the AI ought to move forward rather than continue probing indefinitely.
Set clear standards to terminate the survey: Terminate interviews dynamically in real time when necessary. Configure the AI to cut the interview short if a participant repeatedly fails to offer substance, preventing an unnecessary continuation to the end.
Best Practices: When setting up the logic for moderation, be careful not to make the disqualification rules too strict. A good balance between data integrity and the participant experience is essential, ensuring respondents get a fair chance to elaborate or clear up their points before termination occurs. Taking this approach supports account health metrics, minimizes friction for the participant, and lessens the need for clients to manually filter out subpar interviews after fieldwork concludes.
Estimate accurate LOI: Factor probing into the estimated LOI. To provide respondents with a precise duration estimate, the anticipated interview length must incorporate the maximum number of configured probes.
Add dynamic progress bar settings: The progress bar should accurately indicate overall interview advancement. Rather than pausing or stalling when follow-up probes are presented, the indicator needs to move forward incrementally to reflect the continuous journey of the participant.
Setting appropriate incentives
Traditional survey pricing models rely heavily on LOI to determine what is a fair and appropriate reward for the respondent. For AIMI projects, this is often insufficient as a short video task can feel more demanding than a long survey, and audio and video introduce psychological and technical friction.
We recommend that Project Managers:
Align CPI with perceived respondent effort, not just time
Use Boost CPI when:
Media (audio/video) is involved
Targeting is niche
Early pacing is slow
Boosting CPI improves traffic on a survey that requires higher effort, but does not fix structural issues. If your project continues to experience issues, please ensure it is set up correctly, and respondents can successfully complete the survey.
Learn more about boosting CPI in our FAQs.
See Ensuring Data Quality in AIMI Studies to learn more.