> For the complete documentation index, see [llms.txt](https://help.getmobly.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.getmobly.com/help-center/host/using-the-ai-prompt-builder.md).

# Using the AI prompt builder

Host's event creation flow is AI-first. You describe what you want — the event, the ticket types, what registrants should be asked, what emails to send — and the AI builds the registration page, ticket setup, and email templates in one shot. From there you refine via more prompts, or click into any section to edit by hand.

This article covers how the prompt builder works, what it can build, and when to refine vs. edit manually.

## The basic flow

1. **Describe your event in plain language.** Type a description into the prompt box. Tell it what the event is, what tickets you need, what info to collect from registrants, and what emails should go out.
2. **The AI generates.** Takes about 60–130 seconds. The output is a registration page (with sections you can scroll through), ticket types, and a starter set of email templates.
3. **Refine via more prompts, or edit any section directly.** Want to bump the capacity from 40 to 60? Type that and the AI updates it. Want to tweak a heading? Click in and edit by hand.

The first generation rarely produces the final version. Plan to iterate.

## What a prompt can include

The AI picks up natural-language descriptions of:

* **Event basics** — name, dates, location, audience
* **Ticket types** — paid or free, prices, capacity limits, visibility (public vs. invite-link-only)
* **Promo codes** — code text and discount amount (including 100% discounts for complimentary tickets)
* **Registration form fields** — custom questions beyond the standard name/email
* **Email automation** — confirmation, reminders, what each should say
* **Visual style** — color palette, tone (professional, casual, elevated)
* **Agenda sections** — multi-section agendas including topics, times, speakers, and locations

A working example — the kind of prompt that produces a usable starting point:

> I'm setting up registration for our annual HR summit on March 9–10, 2027. General Admission at $895; promo code COMP27 that fully discounts the ticket for sponsors. Beyond name and email, also collect job title, company, dietary restrictions, and a privacy-policy consent. Email automation: confirmation with ticket attached, one-week-out reminder, day-before reminder. Visual style: professional, navy and white.

You can stop here, run the prompt, and iterate. Or pack more in — the more specific you are upfront, the less back-and-forth.

## Multi-activation events: one prompt per piece

For events with breakouts, roundtables, dinners, or other sub-activations, the cleanest pattern is **one Host event per activation**, plus one for the main event itself.

For a two-day summit with a few breakouts, a panel, and a VIP dinner, that's:

* One main event (the summit registration)
* One Host event per breakout (each free, capacity-limited)
* One Host event for the panel
* One Host event for the VIP dinner (its own paid event)

Each gets its own prompt. The Mobly Hub side stitches them together as activations under the parent event — see [Tracking activations within an event](/help-center/the-hub/managing-events/tracking-activations.md) for how that side works.

## Refining vs. editing manually

Use **more prompts** when the change is structural or you want the AI to do the work:

* *"Add an agenda with three sections — opening keynote, breakout discussions, networking."*
* *"Increase the dinner capacity to 60."*
* *"Add a question asking which workshops they want to attend."*

Use **manual editing** when the change is small and you know exactly what you want — tweaking a single word, swapping a placeholder image, reordering sections via the up/down arrows on each section.

You can mix freely: prompt to scaffold, then manually polish.

## About credits

The AI builder runs on a credit model. **Prompts consume credits; manual editing is free.** That means:

* Use prompts for the heavy lifting (initial generation, structural changes)
* Use manual editing for small adjustments and polish

There's no expiration on a trial — you can take as long as you want — but credit usage is capped. If you run out before your event is ready, contact your CSM.

## Tips for good prompts

* **Lead with the event.** *"I'm setting up registration for \[event name] on \[dates]."* Gives the AI a frame.
* **Be specific about money.** *"$895 / General Admission"* beats *"standard ticket pricing."* The AI doesn't infer pricing.
* **Name your audiences.** If you have multiple segments getting different emails, say so up front — *"Audience segments: members, partners, sponsors — each gets a different confirmation email."*
* **Describe visual style in adjectives.** *"Polished and professional"* or *"warm and casual"* lands. Color palettes work too (*"navy and white"* or *"warm accent — gold or copper"*).
* **Iterate.** First prompt sets the scaffold; subsequent prompts refine. Don't try to cram every detail into one prompt.

## Related articles

* [Getting started with Host](/help-center/host/getting-started-with-host.md) — launching Host for a Mobly event
* [Preparing the event page](/help-center/host/preparing-the-event-page.md) — what the registrant sees
* [Creating email templates](/help-center/host/creating-email-templates.md) — designing the emails the prompt builder generates
* [Selling tickets](/help-center/host/selling-tickets.md) — paid ticket setup


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://help.getmobly.com/help-center/host/using-the-ai-prompt-builder.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
