Conduct customer-discovery interviews by phone
Use a disclosed voice assistant to conduct structured research calls and collect answers for the research team to review.
How this works
Use a disclosed voice assistant to conduct structured research calls and collect answers for the research team to review. Telephone research can scale question delivery, but a transcript is useful only if the participant understood the purpose and the interviewer did not steer answers. This process gathers experiences and open questions rather than turning a research call into sales qualification.
Use a disclosed voice interviewer with a short guide and bounded follow-up rules. Test the conversation on synthetic answers before calling consenting participants. An available voice platform may manage calls; without one, provide an interview script and structured notes template for a human researcher.
Before you start
Research objective
Choose a question about behavior or experience that calls can credibly answer.
Participant permission
Use a consented contact list and confirm the agreed recording and retention approach.
Interview guide
Define neutral opening questions, permitted probes, and escalation or stop phrases.
Prepare the inputs
- participant_list
- Required
Approved contact records
Include consent status and allowed contact window.
- research_question
- Required
One focused question
Avoid combining product research with an undisclosed sales objective.
- interview_guide
- Required
Ordered prompts and probes
Keep questions neutral and avoid compound or leading wording.
- call_settings
- Required
Disclosure and retention rules
Make the voice-assistant identity and recording choice explicit.
- response_schema
- Required
Topic fields
Support declined, unknown, and not applicable separately.
Implementation, step by step
Design the call path
- Translate the research question into a brief guide about recent concrete experiences.
- Choose follow-ups for examples and clarification, with a clear route for refusal or discomfort.
Checkpoint: A short interview flow with stop conditions.
Test synthetic conversations
- Simulate short answers, interruptions, a refusal, and an answer unrelated to the question.
- Check that the assistant does not invent a response, pressure the participant, or continue after a stop request.
Checkpoint: A reviewed test transcript and corrected guide.
Confirm call readiness
- Check contact permission, time window, caller identity, and recording configuration.
- If a voice tool is unavailable, hand the same guide to a human instead of claiming calls were placed.
Checkpoint: A bounded call list ready for the authorized operator.
Run the disclosed interview
- Begin with purpose, automated-interviewer disclosure, and the recording choice.
- Ask the next relevant question, clarify ambiguous responses, and stop when permission or time runs out.
Checkpoint: A consent-aware recording or notes record.
Review the transcript
- Verify speaker turns and consequential details against the recording when available.
- Separate direct answers, interviewer prompts, uncertain transcription, and questions left unanswered.
Checkpoint: An accurate research record with uncertainty markers.
Synthesize without overgeneralizing
- Group observed experiences across calls and retain counterexamples and participant counts.
- Use excerpts to support themes; distinguish the recruited sample from the broader market.
Checkpoint: A research summary and follow-up questions for the team.
Decisions along the way
Participant declines recording
Use the permitted notes-only path or stop if the project requires recording.
Participant asks for product support
Offer the approved handoff and exclude the support exchange from research coding.
Answer contains an unclear number
Ask once for clarification; otherwise retain the uncertainty.
What you will produce
interview-records.csv
CSVEnables researchers to compare answers without unnecessary identifiers.
Include: participant_id · consent_mode · question_id · response · transcript_ref · status
discovery-summary.md
MarkdownSupports learning decisions, not a market-size claim.
Include: research_question · themes · counterexamples · sample_limits · next_questions
Check the result
- Verify disclosure appears before substantive questions.
- Review a sample for leading follow-ups and unsupported paraphrases.
- Ensure refusals and unanswered questions are not coded as negative opinions.
- Link themes to specific transcript passages.
When something goes wrong
Speech recognition misses important terms
Flag the span and review audio or ask a follow-up through the permitted channel.
Calls disconnect repeatedly
Stop the batch and inspect configuration before further attempts.
The agent repeatedly departs from the guide
Return to supervised calls and revise the path before expanding.
A worked example
SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT
Request
Explore why users abandon a scheduling form.
Inputs
Synthetic example. Synthetic participant R1 says the form asked for an account before showing availability; R2 declines the interview.
Expected result
Synthetic expected result. Record account-before-availability as one observed obstacle from R1. R2 contributes a declined status, not evidence that the form is satisfactory.
Run a small pilot
Start small
A small consented group representing a few relevant user situations.
Record the baseline
Compare completed answers, interviewer effort, and transcript corrections with human calls.
Agree success criteria
Agree acceptable transcript accuracy and protocol adherence with the researcher.
Stop or revise
Stop on failed disclosure, withdrawal of consent, or repeated unsupported answer coding.
Keep the scope clear
- Research participation does not authorize sales messages.
- Restrict contact details and recordings to the approved research purpose and retention window.
Check before using
Confirm consent and recording settings. Check the quality of follow-up questions and ground conclusions in participants’ actual responses.
Business activities
- Research customers and markets
FROM A RECIPE TO YOUR WORKFLOW
Bring the company context together.
This workflow needs reliable inputs before it needs a better prompt. Moat8 Vault brings working information into a readable archive for the AI tools you use.
For this recipe: Consenting research participants · Interview guide and follow-up rules · Call recording and retention settings
Start with one recurring task, agree which sources to use, and review the first result with your team.
Discuss this workflow