Skip to content

Latest commit

 

History

History
227 lines (183 loc) · 8.8 KB

File metadata and controls

227 lines (183 loc) · 8.8 KB
title Build Your Onboarding with AI
description Watch an AI assistant build production-ready onboarding — a flow, a checklist, a survey, an announcement and a resource center — in a real app, then follow along with the exact prompts.
icon sparkles

Usertour is open-source user onboarding with an MCP server built in: connect an AI assistant like Claude Code, Cursor or Codex, describe the experience you want, and it authors, themes and publishes the content directly in your project — matched to your app's design, verified in your running app.

The video below does exactly that against a real app (shadcn-admin): four prompts, and after each one — the result live in the app, then the content and data in the Usertour dashboard.

<iframe className="w-full aspect-video rounded-xl" src="https://www.youtube.com/embed/StOBwVbiG-Y" title="Build your onboarding with AI — Usertour MCP demo" allowFullScreen ></iframe>

Before you start

All you need is a Usertour account and an AI assistant connected to the MCP server. With Claude Code that's the plugin (it registers the MCP connection, the authoring skills, and the SDK-install skill in one):

/plugin marketplace add usertour/skills
/plugin install usertour@usertour

Then run /mcp and authorize in the browser — pick the project, the environments, and the access level. That's the whole setup: you don't even install the Usertour SDK by hand — on the first prompt the assistant notices it's missing and wires it into the app itself, then builds the content.

**Self-hosting?** The plugin defaults to Cloud — point it at your own instance before connecting (your exact URL is shown in **Settings → MCP**): `export USERTOUR_MCP_URL="https:///mcp"` **Optional, recommended:** also install the [Chrome DevTools plugin](https://github.com/ChromeDevTools/chrome-devtools-mcp) so the assistant can open your running app, pick element selectors from the real DOM, and verify each experience actually renders before publishing — noticeably better tooltip accuracy.
/plugin marketplace add ChromeDevTools/chrome-devtools-mcp
/plugin install chrome-devtools-mcp@chrome-devtools-plugins

Using Cursor, Codex, VS Code or another client? See the MCP connection guide — every client gets the same one-URL setup, and Settings → MCP in the app shows the steps with your instance's URL pre-filled.

Step 1 — A feature onboarding flow

Using Usertour, build a user onboarding flow for the Create Task feature.

Requirements:
- The visual theme must match the website's existing design.
- The flow must be production-ready and suitable for launch.
- Every step should provide genuine value to users. Avoid adding steps
  simply for the sake of having a flow — the experience should help users
  understand and successfully use the feature.

In the app — before building anything, the assistant notices the app has no Usertour SDK yet and installs it on its own (the loader snippet, init() and identify()); then the flow runs against the real UI: tooltips anchor to the actual Create Task controls, and the styling matches the app because the agent read the design system first and themed the content to it.

In the dashboard — the flow appears under Content with its steps, targeting and a published version; Analytics starts counting views and completions as sessions come in.

Step 2 — An adoption checklist

Create a checklist for the features on the User List page.

Requirements:
- Combine the checklist with relevant onboarding flows to significantly
  improve product adoption.
- Ensure production-level quality.
- Match the checklist's visual theme to the website's existing style.

In the app — a checklist panel lists the User List features as tasks; completing a task can launch the matching flow, so the two content types work as one adoption journey.

In the dashboard — the checklist shows per-task completion in Analytics, so you can see which features users actually adopt and where they stall.

Step 3 — A product feedback survey

Create a survey to collect user feedback about the product's different
features, including:

- Feature ratings
- Overall satisfaction
- Usability feedback
- Suggestions for improvement
- Open-ended comments

The survey should be thoughtfully structured and suitable for production use.

In the app — a multi-question survey renders in the app's own look: ratings, scales and open-text questions in a sensible order.

In the dashboard — every question gets its own breakdown under Analytics: score distributions for the ratings, and the open-text answers collected per response, ready to read through (or to hand back to the AI to summarize).

Step 4 — A welcome announcement + resource center

Use the Usertour MCP to create a production-ready welcome announcement and
improve the Resource Center as one cohesive onboarding experience.

Welcome Announcement — use Usertour's native Announcement feature (not a
Flow):
- Use the speech bubble announcement format.
- Target new users only.
- Welcome users and briefly introduce the product's core value.
- Guide users to the User List page with a clear primary CTA.
- Include a link to https://usertour.io/ explaining that the onboarding
  experience is powered and maintained by Usertour.
- Keep the copy concise, helpful, and professional.
- Match the website's existing visual style.
- Configure sensible display frequency, dismissal behavior, and audience
  targeting.
- Ensure the announcement does not conflict with other active onboarding
  experiences.

Resource Center — make it support the same onboarding journey:
- Add an entry that helps users navigate to the User List page.
- Make the experiences created in the previous steps accessible from the
  Resource Center.
- Organize resources into clear, user-focused groups.
- Use concise titles and descriptions that explain the value of each
  resource.
- Remove or avoid duplicate and low-value entries.
- Match the Resource Center's design to the website's visual theme.
- Configure appropriate visibility and audience rules.
- Ensure all links, actions, flows, surveys, and video content launch
  correctly.
- Make the experience accessible, responsive, and production-ready.

In the app — new users get a speech-bubble welcome pointing them at the User List page, and the resource center becomes the lasting home for everything built above: the flow, the checklist and the survey, organized into groups and launchable on demand.

In the dashboard — the announcement and resource center sit alongside the rest under Content, each with its own targeting and analytics, and Publish history records what went live in which environment.

One more: a one-prompt task

Not everything is a four-step journey — one-off tasks are a single prompt. Here the assistant builds a video modal, verifies the embed actually plays, and leaves it as a draft for review instead of publishing:

<iframe className="w-full aspect-video rounded-xl" src="https://www.youtube.com/embed/vaP2QuhOHLk" title="One-prompt video modal — Usertour MCP demo" allowFullScreen ></iframe>
Use the Usertour MCP to create a one-step modal flow featuring this
YouTube video:

https://www.youtube.com/watch?v=ZIaOBAjvc38

Use the title:

**Sam Altman: "Never a Better Time to Do a Startup"**

Add concise supporting copy explaining why this is a uniquely promising
time to build a startup and what viewers can learn from the video.
Include a clear watch action and an easy way to close the modal.

Match the product's visual style, verify that the video embed works
correctly, and save the flow as a draft.

Where to next

The other half of the loop — five prompts that turn the collected data into rankings, funnels and survey readouts. Install the SDK and identify your users — everything above builds on it. Connect any client, see every tool, understand scopes and read-only mode. Prefer hands-on? Build the same flows, checklists and surveys visually. Run the whole platform — MCP server included — on your own infrastructure.