The lab at a glance

The fastest way to learn the shape of User Sage is to open the lab and follow the Checkout redesign from question to decision. This chapter names each part so the clicks later make sense.

The flow

Day one is Study → panel → Findings. Live sessions are a parallel path: run them on their own the traditional way, or create a study you use in a live session. Teammates can watch from the Observation Lounge either way.

You bring a decision you cannot answer yet. Example from the lab: why people stall at the shipping step.

Study Brief (optional). You tell User Sage what you need to learn. It drafts a Brief covering the decision, a recommended method and why, who to ask, and a study plan. You review it, edit it, then create a study from it. The Brief and the study stay linked. You can also start a blank study and skip the Brief.

Study. You pick a method (or combine methods) and configure the tasks, screens, and questions. For Checkout, a First‑Click Test on the new shipping screen is a solid place to start. That study is what you run with an AI Panel, Your Panel, or both. There are seven unmoderated methods. The same study can also be the thing you walk through in a live moderated session when you want conversation instead of (or after) async responses.

AI Panel (simulated people). The Sage Engine builds each simulated person from your participant model, with their own habits, limits, and patience. They work through your screens and questions. Treat the result as a hypothesis to test with real people, not a finding.

Real participants. Give real people the same task. Invite your own through Your Panel, or let GenPop Panel find screened participants. Their responses are the evidence you test the hypothesis against.

Pulse. Each panel gets its own Pulse gauge: Good, Watch, or Needs work. Pulse checks whether responses look realistic, varied, and consistent. It does not decide whether they are true. Filling in product context helps on AI Panel. When a decision matters, confirm with participants.

Findings. Simulated and real results sit in separate columns, with takeaways and a written summary. You always know which result came from where. Kept separate, never blended.

Live sessions (parallel path). Moderated research is not only a follow‑up after Findings. You can run a live session on its own, the way teams traditionally interview or moderate usability. You can also create a study and use that study in the live session. You lead the call; teammates watch from the Observation Lounge; the recording and transcript stay with the session after consent.

Around the flow

Incentives. Real participants give you their time. Set an incentive for the study and track it per person, from promised to given.

Your AI tool. Over MCP (Model Context Protocol), the AI tool you already use can plan a study, run a panel, and read findings from chat. Connect on any plan. Depth depends on Free vs Pro (see chapter 9).

Project. Brief, studies, and Findings stay linked in a Project (the lab uses Checkout redesign) so anyone can trace the decision back to the evidence.

Seven methods

Survey, 5‑Second Test, First‑Click Test, Prototype Test, Tree Testing, Card Sorting, and Preference Testing. You can combine several in one study. Live moderated sessions are a parallel path when you need a live interview or moderated usability test. Chapter 10 is a short chooser for what to run next. The lab’s “Seven ways to ask” section shows each method on the same Checkout story.

What to do with this chapter

Open usersage.com/lab, click through the parts once, and come back here when you are ready for the workspace map.