New Member Onboarding

What it does

A personal welcome with a first-week plan, a day-3 check-in and a two-week “book a session” email, each written from the member's own answers.

• Starts when your sign-up or intake form posts a new member's answers to the workflow's webhook.
• AI writes a personal welcome with a 2–4 step first-week plan from their goals, experience and preferred times, using only your classes, booking link and intro offer.
• Sends the welcome straight away; it waits for a staff look when the member mentions an injury or health condition, or for every welcome if you ask.
• Waits 3 days, then emails a short check-in written from their answers.
• Waits 11 more days, then emails a “how's it going?” note inviting them to book a session or class.

What it needs

• A paid plan (agents run live on paid plans; the waits also need the Wait step enabled on your workspace).
• An AI provider key (Settings → AI Providers).
• A sign-up form on your site that posts to the webhook, with an email field.
• Your classes, booking link and any intro offer.

What it doesn't do

• It's non-clinical: it gives no health, injury, nutrition or weight-loss advice and promises no results.
• It doesn't know whether the member has visited (no check-in data), so the emails don't react to attendance.
• It doesn't read replies or book sessions; replies go to your front desk. To stop the later emails for someone, cancel their waiting run in History.
• It isn't a list-based drip campaign: each member gets their own three emails from their own answers.

Availability and plans

Included free on the Enterprise plan; on other paid plans it's a one-time purchase per workspace (the price is on the Agents page). The Agents page in the app always shows its current status.

Before you start

• A paid plan: agents run live, and the Free plan only runs Dry Runs.
• An AI provider key (OpenAI, Anthropic, Google and more) in Settings → AI Providers. AI usage is billed by your provider.
• No app connections: it only uses built-in steps.
• A form, app or system that can send each new item to a webhook URL (the agent starts from a webhook).
• About 15 minutes.

• Bring your own AI key

Set it up step by step

Get the agent first (buy it, or it's already yours when your plan includes it), then in Agents → My agents press “Set up this agent”. That creates the agent's workflow in your workspace (it counts towards your plan's workflow limit) and opens the canvas with a setup checklist above it. Each item links to the exact place to go and ticks itself off when it's done.

1. Connect your AI provider

The AI steps run on your own key (OpenAI, Anthropic, Google and more). Add one in Settings → AI Providers.

• Connect your AI provider

2. Describe your studio

Open “Write the welcome and first-week plan” and replace the placeholder with your classes, booking link, intro offer and sign-off.

3. Add your front-desk inbox

Open each of the three email steps and enter the inbox members' replies should go to.

4. Test it with Dry Run

Press Dry Run: the agent runs on sample data with no messages sent and nothing written to your apps.

• Dry Run vs Run

5. Switch the trigger on

Open the trigger, copy the webhook URL and signing secret into your sign-up form, and switch it on.

How it works

The agent is a normal workflow with 14 steps (3 AI steps, with a person approving in Reviews). You can open, edit and monitor it like any other workflow.

• New member sign-up from your form — Starts when your form or app sends data to the agent's webhook URL. Your sign-up or intake form posts each new member's answers (name, email, goals, experience, preferred times) to the workflow's webhook URL.
• Write the welcome and first-week plan — AI step (runs on your AI provider key). AI writes a personal welcome email with a simple first-week plan built from the member's goals, experience and preferred times, using only your classes and offers. It flags sign-ups that mention an injury or health condition for a staff look.
• Send, check first or skip? — Decision: picks the branch to follow. Sign-ups without an email are skipped; welcome emails that mention a health issue (or all of them, if you ask) wait for a staff look; the rest are sent straight away.
• Not sent — Kept in the run history. Branch: Skip. The run history keeps the sign-up and why no emails were sent.
• Check the welcome email — A person approves or rejects it in Reviews (the run waits). Branch: Staff look first. Optional: when you ask to review every welcome, or the member mentions an injury or health condition, a staff member reads and edits the welcome in Reviews before it's sent.
• Not approved — Kept in the run history. Branch: Rejected. Rejected welcomes are kept in the run history; no emails were sent.
• Email the welcome — Sends an email from your workspace's sender. Branch: Approved / Send. Sends the welcome and first-week plan to the new member, with replies going to your front desk.
• Wait 3 days — Waits 3 days. Pauses the run for 3 days after the welcome (Dry Run doesn't wait).
• Write the day-3 check-in — AI step (runs on your AI provider key). AI writes a short, friendly check-in from the member's goals and first-week plan, inviting questions and nudging the next step.
• Email the check-in — Sends an email from your workspace's sender. Sends the day-3 check-in to the member.
• Wait 11 more days — Waits 11 days. Pauses the run until about two weeks after sign-up (Dry Run doesn't wait).
• Write the two-week email — AI step (runs on your AI provider key). AI writes a “how's it going?” email that invites the member to book a session or class that fits their goal.
• Email the two-week note — Sends an email from your workspace's sender. Sends the “how's it going / book a session” email to the member.
• Onboarding sent — Kept in the run history. The run history keeps all three emails.

Test it with Dry Run

Press Dry Run in the canvas. The agent runs on the sample data stored on its trigger (the “Sample data for Dry Run” box), so you can check every step's output before anything is live. Edit the sample to match the fields your own form or app sends.

Sample data fields

name, email, membership, goals, experience, preferred_times, anything_else, signed_up_at.

• Nothing is sent or written: app actions, emails and Slack posts are simulated, and AI steps don't call your AI provider.
• Approval steps use the Dry Run decision you pick in the step's settings (approved, rejected or timeout), so you can try each branch.
• Wait steps don't wait: they report how long they would wait and the run goes on.

Go live

• Open the trigger, copy the webhook URL and signing secret into your sign-up form, and switch it on.
• The webhook is protected by a secret: send it in the header shown in the Activation panel (requests without it are refused with 403). Each request starts one run.
• The setup checklist adds a “paid plan” item before activation: live runs need a paid plan (the Free plan only runs Dry Runs).
• When every checklist item is done and the trigger is on, the checklist says “Live — this agent is running”. Follow its runs in the workflow's History tab and in Analytics → Agents.

• Webhook triggers
• Switching a trigger on (Activation)

Questions

Does it know whether the member has come in?

No. It has no check-in or attendance data, so the emails never assume either way. A version triggered by Square sign-ups can follow once Square is approved.

Can I approve the welcome email first?

Yes. Write “Review the welcome email: yes” in your studio details. Welcomes that mention an injury or health condition always wait for a staff look.

How do I stop the later emails for someone?

The agent doesn't read replies. If a member asks you to stop, cancel their waiting run in the workflow's History.

Troubleshooting

• “No AI provider connected” or a rejected key: connect or fix the key in Settings → AI Providers, then press Test there.
• A checklist item stays unticked: the setting is still empty or still contains its placeholder text. Open the step from the checklist and fill it in.
• Nothing happens when your form sends data: check the webhook is switched on and the request carries the secret header (403 means it's missing or wrong).
• A run shows as paused: it's waiting for someone in Reviews to approve or reject it.
• A run shows “Waiting until …” in History: that's a Wait step; it continues on its own (it can be cancelled through the API).
• A step failed: open the run in History and check that step in the Trace tab for the error and what it received.

• Debugging failed runs
• Error messages
• Get help