What is synthetic research?

Synthetic research uses AI-powered personas that simulate how real buyers, customers, or market segments would respond to your research questions. It produces directional signal — insights to sharpen your hypotheses — before you invest in real primary fieldwork. Gather Synthetic runs AI-moderated interviews across any audience archetype in minutes, not weeks.

How is synthetic research different from real research?

Synthetic research generates directional signal using AI personas, while real primary research collects data from actual people. Synthetic pre-research is faster (minutes vs. weeks), cheaper, and ideal for hypothesis generation and stakeholder alignment. It is not statistically valid and should be used to focus and prioritize real fieldwork, not replace it. Gather offers both synthetic pre-research and real AI-moderated interviews with actual respondents.

What types of research can Gather Synthetic run?

Gather Synthetic supports 14 study types: Brand Perception, Product Feedback, Concept Testing, Competitive Intelligence, CX/NPS Deep Dive, Messaging & Claims Testing, Win/Loss Analysis, Market Segmentation, Pricing Research, Ad & Creative Testing, Customer Journey Mapping, Feature Prioritization, Churn & Retention Analysis, and Audience Discovery.

How much does synthetic research cost?

The first 5 synthetic interviews are free. After that, B2C audience interviews cost $0.50 each and B2B audience interviews cost $5.00 each. There is no subscription required.

How accurate is synthetic research?

Synthetic research is directional, not statistically accurate. Confidence scores reflect internal AI response consistency, not statistical significance. Quantitative projections carry a ±15–20% margin of error. Treat findings as educated hypotheses to validate with real primary research, not as definitive measurements.

← All brands

Language learning & subscription adoption · PUBLIC RESEARCH BRIEF

DuolingoWill the first AI conversation earn a second?

Duolingo’s current Max overview describes Video Call and Roleplay as AI-powered learning features. Its Video Call article describes conversations with Lily and the option to skip a call when speaking is inconvenient. These are existing feature descriptions, not a new launch claim; the research question is what would make adult learners try and repeat conversation practice.

Sources checked 2026-09-19 · Simulation results not yet generated

Test a question in Gather ↗Explore fictional demo →

CHANGE ONE THING. LEARN WHAT MATTERS.

Three questions for the GTM team.

For eligible adults considering Duolingo Max, would a message about practicing a familiar real-life situation or one about having an open-ended AI conversation make the first session feel more worth trying? Keep subscription terms constant and separate interest from willingness to speak aloud.

Set up this study →

What would make an adult Duolingo learner return to Video Call after the first attempt? Compare learners who completed the call with those who chose to skip, and ask about setting, difficulty and available time without assuming why they stopped.

Set up this study →

Would introducing an eligible Duolingo Max learner through a guided Roleplay scenario or a Video Call better fit their immediate goal? Treat the sequence as a proposed onboarding experiment, not a current product promise. Identify when a learner would prefer ordinary lessons instead.

Set up this study →

PROPOSED AUDIENCE

Who should weigh in?

US adults learning a language in Duolingo who are eligible for the relevant Max feature on their course and device. Include free users considering an upgrade, current subscribers and former subscribers, with travel, family and general-interest goals. Exclude children and high-stakes proficiency or employment assessments. Proposed research audience only.

TWO TIME HORIZONS

Trial today. A habit tomorrow?

Near term · 0–90 days

Over 0–90 days, test comprehension of the feature and willingness to start, then observe consented first and repeat sessions. Record skipped calls and the reason the learner gives. A paid trial, a completed conversation and a second voluntary session are different measures.

Longer term · 3–12 months

Over 3–12 months, follow whether conversation practice remains part of the learner’s routine and whether it contributes to their decision to renew. Separate novelty, an upcoming trip and sustained interest. Do not equate a streak or subscription renewal with demonstrated language proficiency.

What would make the result actionable?

Use eligible adult cohorts, current plan terms and consented usage data. Compare onboarding variants while controlling for course, device and prior practice. Track starts, skips, repeat sessions and actual renewals; any claim about speaking improvement needs a separate, appropriately designed assessment with independent raters.

A Gather simulation returns hypothetical customer reactions. Quantifying revenue, traffic or retention needs actual business inputs and validation against observed behavior.

Public sources

Duolingo Max overview, originally published March 14, 2023 ↗Published 2023-03-14

Duolingo Video Call with Lily, originally published September 24, 2024 ↗Published 2024-09-24