About this AI skill
The Customer interview analysis skill is pre-built for Elle (the AI assistant in Aha! software) and reviews a full interview transcript in Aha! Discovery or a note. It separates customer requests from underlying needs and produces an analysis with participant context, direct quotes, and severity ratings supported by evidence from the transcript. The output includes matching ideas in your workspace, one-line suggestions for needs not covered by existing ideas, and gaps in what the interview covered.
The full Customer interview analysis skill, as Elle uses it:
# Customer interview analysis
Use after a customer interview to surface the feedback that should change what you build, and connect it to ideas already in the workspace.
## Definitions
Use these meanings consistently in every step.
- **Interview:** The interview record or note holding the transcript, or the record whose link the user pasted into the chat
- **Point of feedback:** One thing the customer said that carries a need, a blocker, or a workaround. Not a topic, a specific statement.
- **Severity:** How much the issue costs the customer. High means they are blocked or paying for a workaround. Medium means friction they tolerate. Low means a preference.
- **Existing idea:** An idea already in the workspace that covers the same need
## Workflow
1. Read the full transcript. Do not summarize from the first few exchanges.
2. Identify the participant and their role, and note which product areas they actually use. Feedback from a non-user of an area carries less weight and should be marked as such.
3. Extract the points of feedback. Quote the customer's own words for each one; paraphrasing loses the signal that makes the point actionable.
4. Rate severity for each point and state the evidence behind the rating, such as a described workaround, a lost deal, or an abandoned workflow
5. Separate what the customer asked for from the problem underneath it. Customers describe solutions. The underlying need is what should inform the roadmap.
6. Search the workspace for existing ideas that match each need. Cite them by reference number and name.
7. Suggest new ideas only where nothing existing covers the need, and draft a one-line description for each
8. Note what the interview did not cover that would change the interpretation
## Rules
- If no transcript is available, ask for the interview record or note before analyzing
- Quote the customer directly for every point of feedback
- Never present a paraphrase as a quotation
- Distinguish the stated request from the underlying need, and label which is which
- Reference interviews, ideas, and features by reference number and name
- Do not create ideas or link records. Present the analysis and let the user apply it.
- Headers use sentence case. No em dashes, en dashes, or curly quotes.
## Output
```
## Participant
<who they are, their role, and which areas they use>
## Key feedback
| Quote | Underlying need | Severity | Evidence |
## Matches existing ideas
| Need | Existing idea | Why it matches |
## Suggested new ideas
| Need | Draft idea | Why nothing existing covers it |
## Not covered
- <what would change the interpretation if known>
```
## Quality checks
- Every point of feedback carries a direct quotation
- Stated requests and underlying needs are labeled separately
- Every severity rating cites evidence from the transcript
- New ideas are proposed only where the search found no existing coverageTry this AI skill now
Open the Customer interview analysis skill in Aha! Discovery to identify customer needs and find ideas that address them.
Open this AI skillAbout Elle
Elle , the AI assistant in Aha! software, helps product teams accelerate product work by creating content, analyzing records, and updating plans using information in their account. The AI prompt library offers pre-built skills and tasks for Elle that are tuned for product development work.