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. Predictive accuracy and a statistical interval are only shown when established for the specific result. Treat findings as educated hypotheses to validate with real primary research, not as definitive measurements.

← All brands

Continuous integration & test intelligence · PUBLIC RESEARCH BRIEF

CircleCIWhich rerun cue helps a team fix a flaky test instead of normalizing an uncertain build?

CircleCI currently documents Test Insights for reviewing recent test performance, failures, slow tests and tests labeled flaky. It also documents rerunning failed tests from the same commit when test-result prerequisites are met. A passing rerun may reflect a transient failure; it does not establish that the original defect is resolved. This brief studies how teams interpret and act on reruns.

Updated 2026-10-10 · 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.

When a failed test is labeled flaky, would a commit-and-history evidence card or a quarantine and ownership prompt better help a developer choose between rerun, investigation and release blocking?

Set up this study →

After a failed-test rerun passes, would a side-by-side first-run comparison or a persistent uncertainty badge better prevent a release reviewer from treating the result as proof of a fix?

Set up this study →

When slow and frequently failing tests compete for attention, would a release-risk queue or a runtime-savings queue better help a platform team choose what to repair first?

Set up this study →

PROPOSED AUDIENCE

Who should weigh in?

North American software engineering, quality, developer-platform and release teams using or evaluating CircleCI, including developers, test owners, CI administrators, engineering managers and release approvers. Recruit participants with different test suites and release-risk responsibilities. Proposed audience; no production repository, test result, artifact, secret or developer identity is included.

TWO TIME HORIZONS

Trial today. A habit tomorrow?

Near term · 0–90 days

Over 0–90 days, test synthetic pipelines and JUnit-style results with seeded deterministic failures, intermittent failures and slow tests. Measure correct classification, unnecessary reruns, investigation choice, release decisions and time to an evidence-backed next step. Trigger no production workflow.

Longer term · 3–12 months

Over 3–12 months, follow consenting teams in sandbox or de-identified projects as test suites, ownership and release cadence change. Examine quarantine debt, recurring flakes, rerun dependence and confidence in build status. Delivery impact requires observed release outcomes.

What would make the result actionable?

Use versioned CircleCI documentation, synthetic commits and test histories with hidden failure causes, controlled reruns, timing fixtures and task logs. Hold the commit constant, distinguish test-file from individual-test behavior, score false release confidence separately, and retain no source code or secrets.

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

About CircleCI

Visit the company website ↗