AI for interface design

Member lesson

Research and synthesis with a model

Lesson 10 of 11 in AI for interface design.

50. Responsible AI Use for Research Analysis (feat. Alexander Knoll, Co-Founder of Condens.io) · NNgroup
Lesson

A model is good at the mechanical half of qualitative research: transcribing, tagging by theme, pulling every mention of a topic, summarising forty interviews into something readable. That used to be a week and it is now an afternoon.

A crowd of small figures all face and point to the left. On the right, a researcher with a notebook turns away from them and kneels to listen to the one figure facing the other way.
The crowd is the summary. The one facing the other way is often the finding.
Member

The rest of this is for members.

You have read the opening of this lesson. The rest of it comes with a membership.

One membership covers all four courses and Brands.

  • All lessons in the four Learn courses
  • All brand breakdowns in the Brands section
  • All quizzes, flashcards and crosswords
  • An AI teacher on every lesson, for up to 60 questions a day
  • All course material published during the membership

Price

Membership is from $12 a month on the Yearly plan, which is charged at $144 once a year. Lifetime access is $59, paid once.Membership is from ₹200 a month on the Yearly plan, which is charged at ₹2,400 + GST once a year. Lifetime access is ₹3,999 + GST, paid once.

Check what stuck

Members only

You can't take this check yet.

Members answer these 3 questions and keep the ticket for this lesson. Every lesson has one.

  1. Question 1, locked

    Which of these words means this? “Turning raw research into findings. The slow, valuable part.”

    • Synthesis
    • Edge case
    • Error state
    • Loading state
  2. Question 2, locked

    Which of these words means this? “Tagging transcript passages by theme. Tedious, and now partly automatable.”

    • Coding (research)
    • Fidelity
    • Acceptance criteria
    • Silent failure
  3. Question 3, locked

    Which of these words means this? “Finding what you expected. A model asked a leading question will oblige.”

    • Confirmation bias
    • Edge case
    • Error state
    • Loading state

Elsewhere in the library

Hear about new courses.

Leave an email and we will tell you when something new lands. We do not write often.