Tellet vs User Intuition: AI Interviews, Pricing and Depth

User Intuition’s 5–7 levels of laddering draw on Reynolds and Gutman’s original laddering research (1988). A customer saying “it costs too much” might mean an unaffordable price, a benefit they never experienced, or a risk they cannot justify. User Intuition follows concrete examples to distinguish those explanations and keeps findings connected to their source interviews. Those distinctions help a team choose between testing a price change, improving the product experience, or addressing a specific risk in its messaging. See how User Intuition applies laddering.

Tellet’s interview platform supports dynamic follow-ups and voice, video, and photo responses. User Intuition uses the learning goals to guide deeper exploration of the participant’s experience, with supporting quotes retained in the findings.

User Intuition lets research teams and agencies run multiple studies and audiences in parallel without an hourly interview cap. Start with five-minute self-serve setup and review findings as quality interviews finish. Specialist audiences are recruited to order.

Tellet’s solution overview describes its interview-and-analysis workflow and invites teams to arrange a demo. For a deadline, confirm the time to access, prepare the guide, recruit the audience, and review findings.

With User Intuition, an available customer audience can receive interview invitations as soon as the study is ready. Panel recruitment can add perspectives your customer list does not cover. Narrow eligibility requirements or a difficult-to-reach audience add recruitment time, while concurrent interviewing lets available participants complete sessions without waiting for a moderator.

Five User Intuition quality voice interviews cost $150 in platform fees with your own participants, or $300 with standard panel recruitment. BYOP incentives are separate; specialist audiences require a recruiting quote.

Ask Tellet for the platform charge, interview allowance, recruitment, incentives, and commitment. Use the total for your intended audience and study size when comparing costs.

User Intuition’s transparent pricing gives research teams and agencies a concrete budget before committing to a client follow-up. Five interviews illustrate the entry price; evidence needs determine whether the study should be larger.

User Intuition checks interviews against the research brief so your budget covers conversations with relevant detail. If the study concerns a recent purchase, useful answers should describe the decision and its consequences, not just general opinions about the brand. User Intuition assesses that depth and coverage before billing. An interview that fails the checks is not charged, so researchers can focus on interpreting the usable evidence rather than requesting refunds.

For Tellet, establish which failures qualify for a replacement or credit and whether platform and participant charges receive the same treatment. Include incomplete sessions, shallow answers, and ineligible participants in that discussion.

User Intuition’s evidence review assesses relevant experience, depth, variation, and competing explanations. For each learning goal, its review shows what the evidence supports, what limits the conclusion, and what that means for the research decision. It prioritizes the gaps that could change the recommendation, helping your team choose a follow-up audience and question that distinguish between competing explanations.

User Intuition’s evidence review is informed by Malterud et al.’s information power framework, which emphasizes the relevant information interviews provide, and Hennink et al.’s saturation research, which distinguishes identifying a theme from understanding it in depth.

User Intuition applies these principles to assess whether existing interviews contain enough relevant detail to answer your research question. It can recommend deeper analysis when the evidence is already available, or targeted follow-up interviews when important experiences or explanations are missing. Further paid work requires your team’s approval.

For example, we interviewed 43 Walmart shoppers to understand how they made purchase decisions, where they encountered friction, and what would bring them back. Five shoppers described difficulty choosing between product variants. That points to a practical next question: would clearer product information help them choose? User Intuition recommends testing the current information against a simple comparison guide with recent category shoppers, then exploring what makes the decision easier.

Explore the Walmart study and sample presentation, including the interviews, findings, and two recommended follow-up studies.

User Intuition’s agent access connects existing evidence, research planning, recruitment estimates, study execution, and findings. Researchers can ask an assistant to inspect what is known before preparing a new study, monitor approved interviews, and bring source-linked findings back into their working environment.

For example, ask why customers abandon a purchase after comparing options. The assistant can search previous studies, draft a brief for people with recent experience of that decision, and estimate the recruitment cost. After your team approves the plan and spend, it can launch interviews, check progress, and retrieve findings with supporting quotes.

User Intuition returns the findings and source material to the assistant, so your team can prepare a recommendation and follow-up without reconstructing the study context. For a Tellet integration, confirm whether your plan includes study creation, launch, status, and retrieval of supporting source material.

User Intuition’s synthetic participants help your team explore how people interpret an interview question and identify useful follow-ups for the guide. The models start with real people who have opted in. Their research responses provide the basis for extracting individual traits, habits, and behaviors. User Intuition then compares synthetic responses with real responses from the same respondents and uses the differences to iteratively calibrate the models.

The purpose is to preserve the experiences and behavioral differences that generic LLM feedback can flatten. Accuracy is evaluated against actual respondent answers, so calibration has a human reference point throughout the process.

This approach is informed by Park et al. (2024), who built simulations from interviews with 1,052 people. On the General Social Survey, those simulations reproduced participants’ answers 85% as accurately as participants reproduced their own answers two weeks later. The study demonstrates the value of grounding simulations in individual interviews and measuring them against the people represented.