HomeCasa Jobs to Be Done analysis from interviews, reviews or survey answers
Turn interview notes, reviews or open-ended answers into customer jobs, forces of progress and desired outcomes, with every insight backed by real quotes. Designed for ChatGPT, Claude, Gemini and Microsoft Copilot. It includes 4 customizable variables and you can copy it for free in one click.
Advanced · Text · Pending editorial review
Prompt
Act as a product researcher who is an expert in Jobs to Be Done (JTBD) theory. Analyze real customer data and work out what customers "hire" my product to do.
Context:
- Product or service: {{product}}
- Customer segment analyzed: {{segment}}
- What I will use the analysis for: {{goal}}
- Customer data (interview notes, reviews, open-ended answers, tickets):
{{data}}
Before starting, tell me whether the data is enough to draw conclusions or whether it is thin or biased (for example, only 5-star reviews).
Deliverables:
1. Job statements in the format "When [situation], I want to [motivation], so I can [outcome]". Split them into functional, emotional and social jobs.
2. The four forces of progress: push (what makes them look for something new), pull (what attracts them to the solution), anxiety (what holds them back) and habit (what ties them to the old way). Each one with quotes as evidence.
3. What they "fired" to hire us and what we really compete with, including doing nothing.
4. Buying moment: the specific event that triggered the search.
5. Desired outcomes ranked by importance and by how poorly they are served today; if the data does not support this, label them as hypotheses.
6. Implications for {{goal}}: 3-5 concrete actions.
7. Gaps: what cannot be concluded from this data and what to ask in the next interviews.
Constraints:
- Every insight must come with at least one verbatim quote and its source ID (if the data has no IDs, number each item D1, D2… before you start). Do not invent quotes or present paraphrases as verbatim.
- Show how often each theme appears (n mentions) and do not generalize from a single case.
- If the material contains personal data, do not repeat it in the output.
Format: tables for jobs and forces, bullet points for implications and gaps.How to use it
- Gather 10-30 customer snippets and number each source (I1, R2…). 2. Remove names and personal details before pasting. 3. Use the gaps found to plan your next round of interviews.
Usage example
Product: recipe app for 20-minute meals · Segment: working parents · Goal: marketing messaging · Data: 12 interview notes and 25 app store reviews.
Sample output
Data check
There are only two snippets (I1 and R1). They support hypotheses, not conclusions: n = 1 per theme.
1. Job statements
| Type | Statement | Evidence |
|---|---|---|
| Functional | When my doctor tells me my blood pressure is high, I want to start exercising under supervision, so I can improve my health without getting hurt. | I1: "I signed up after my doctor told me my blood pressure was high…" |
| Emotional | When I work out, I want to feel someone is paying attention to me, so I don't feel like just a number. | R1: "Best part is the coach knows my name and corrects my form…" |
2. Forces of progress
| Force | Hypothesis | Quote | n |
|---|---|---|---|
| Push | Doctor's warning | I1 | 1 |
| Pull | Personal attention from the coach | R1 | 1 |
| Anxiety | [No data] | — | 0 |
| Habit | [No data] | — | 0 |
4. Buying moment
A warning from the doctor (I1). Hypothesis: the trigger is a health event, not a New Year's resolution.
6. Implications
- Test a welcome message built around "starting safely".
- Keep groups small so coaches know every member by name.
7. Gaps
- We do not know what worried them before joining: ask "What almost stopped you from coming?"…
Key facts
- Category
- Business & entrepreneurship · Customer research
- Output type
- Text
- Level
- Advanced
- Designed for
- ChatGPT, Claude, Gemini and Microsoft Copilot
- Verified in
- Pending editorial verification
- Variables
- Product or service, Segment analyzed, Use of the analysis and Customer data
- Language
- English
- Price
- Free, no sign-up
- Updated
- Nov 7, 2026
Frequently asked questions
What does it mean that a customer "hires" a product?
It is the core JTBD metaphor: people do not buy products for their features but to make progress in a specific situation. Understanding that progress explains why they buy better than demographics do.
Can I use only online reviews?
Yes, but reviews skew toward extremes and rarely explain the buying moment. Combine them with at least a few interviews about the last time the customer switched solutions.
What is this prompt for?
Turn interview notes, reviews or open-ended answers into customer jobs, forces of progress and desired outcomes, with every insight backed by real quotes.
Which AI tools does it work with?
It is designed for ChatGPT, Claude, Gemini and Microsoft Copilot. We have not verified it in these tools yet, so results may vary between them.
How do I customize the prompt?
Click “Customize” and fill in the variables (Product or service, Segment analyzed, Use of the analysis and Customer data). The text updates instantly and you can then copy it in one click. Values are stored only in your browser.
Do I need experience to use it?
It is advanced: it is meant for people with experience in the topic who can evaluate and adjust the result.
Is this prompt free?
Yes. Every HomeCasa Prompts prompt is free, with no sign-up or subscription. You can also use them in professional projects.
Can I trust the AI output?
Treat it as a high-quality draft: always check data, figures and important claims before publishing or making decisions.