Tag
Interviews on The Latent Daily: 1 story and 2 prompts. Latest: How to prepare for an AI or machine learning job interview.
The typical stages of AI and machine learning job interviews — coding, ML fundamentals, system design, project deep dives — and how to prepare for each.
thelatentdaily.com Editorial Team3 min read
You are a user researcher. Write an interview script for the study below. Product or topic: [WHAT WE ARE STUDYING] Research goal: [WHAT WE NEED TO LEARN, e.g. "how small landlords track repairs today"] Decisions this research will inform: [e.g. "whether to build a repair-tracking feature"] Participants: [WHO, AND HOW THEY WERE RECRUITED] Interview length and format: [e.g. "45 minutes, video call"] Assumptions we want to test: [LIST OUR BELIEFS, e.g. "landlords use spreadsheets"] Produce: 1. An introduction script: purpose, consent to record, no right or wrong answers, permission to stop. 2. Warm-up questions (5 minutes) about their context. 3. Core questions (most of the time) about specific past experiences, e.g. "Tell me about the last time...". Group them by theme and give a time estimate per section. 4. Neutral probes to use after any answer, such as "What happened next?" or "Why was that important?". 5. A wrap-up with "Is there anything I should have asked?" and next steps. 6. A note-taking template with columns for quote, behaviour, pain point and surprise. 7. A bias check: list any question in the draft that is leading, hypothetical or asks about future behaviour, and rewrite it. Rules: do not mention our product idea until the final section, if at all. Prefer questions about what people did over what they would do. Map each assumption to the questions that test it.
Works with: ChatGPT, Claude, Gemini, Any LLM
You are a qualitative researcher. Help me with a first-pass thematic analysis of the interview transcripts below. Research question: [WHAT YOU WANT TO UNDERSTAND] Context: [e.g. "8 interviews with nurses about shift handovers"] Approach: [e.g. "inductive: let themes emerge" or "deductive: use these codes: ..."] Transcripts (participants labelled P1, P2, ... with personal details removed): """ [PASTE TRANSCRIPTS] """ Steps: 1. Initial codes: list short codes (2-5 words) with a one-line definition each. 2. Themes: group codes into 4-7 themes. For each theme give: - Name and a 2-sentence description. - Which participants mention it (e.g. "P1, P3, P4 - 3 of 8"). - 2-3 verbatim quotes with participant labels. Quote exactly; do not paraphrase inside quotation marks. 3. Divergent views: where participants disagree or a single participant says something important that does not fit. 4. Relationships: how themes might connect (e.g. one appears to cause another), labelled "TENTATIVE". 5. Limitations of this first pass: what a human analyst should check. Rules: - Do not report a theme supported by only one participant as a pattern. - Do not infer feelings or motives that participants did not express. - Keep my research question in focus; put off-topic material under "Other observations".
Works with: ChatGPT, Claude, Gemini, Any LLM