AI Agent for qualitative research
An AI Agent to speed up qualitative user research analysis.
Context
What does it do ?
To keep in mind
The flow
Time saved
Tools
For a skydive log project with the French Skydive Federation, I built an AI agent in n8n to automate user interview analysis and save time and money.
In seconds, it spots patterns, problems, and generates insights—like an affinity diagram partner. The workflow works with Notion or Airtable, depending on where interviews are stored.
Despite saving time, some key steps still need to be done manually:
Identify and filter relevant data
Review results for bias and accuracy
We still need to go over the results to ensure they make sense, as AI can still make mistakes: "Treat AI's work as a first pass, double-check their facts, and provide specific instructions."
The AI prompt is crucial. It’s what generates the result. Therefore, it’s necessary to go through several iterations to achieve the desired outcome.
Trigger the workflow on each update
Get the user interviews from the Google Sheet
Merge all rows in one single content
Let the AI make the report according the prompt
Create the HTML Version of the report
Convert the HTML into a PDF
Upload the PDF into Google Drive for the team
Time without AI:
Preparation: 1 to 3 hours
Affinity diagram: 2 to 6 hours
Total: 4 to 10 hours (about 1 to 2 full workdays)
With my AI agent:
Automated analysis + recommendations: just a few seconds
Manual review and verification: estimated 30 minutes to 1 hour, depending on complexity
Time saved:
Between 3 and 9 hours, up to 90% time reduction
Practically, that’s at least 1 full day saved, and up to 2 days for complex projects.
Thanks to the AI agent, I save up to 9 hours of work per analysis, while maintaining quality control through targeted review.
n8n, HTML & CSS, PDFShift, a bit of JavaScript, and some APIs.