The moment it happens

Spot VIP registrants from their answers

Slack tells you when a registrant looks like an investor or founder, based on what they wrote.

Runs: The moment it happens
Apps: Luma
AI: Yes, uses the built-in AI allowance
Access: calendar API key

Send this to your assistant

Create a ClickRuntime automation: when someone registers on Luma, have AI sort their answers into investor, founder, student or other, and message me in Slack about investors and founders.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Add to ChatGPT Add to Claude

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

Event organizers who use Luma often add questions to the registration form: company, role, what do you want to learn. With a hundred registrants that is a wealth of information, but nobody reads it all. The investor, the potential customer or the speaker's biggest fan is hiding in the list, and the host only finds out when they meet at the door, or never.

When someone registers, Luma sends an event to ClickRuntime. The built-in AI reads the answers to your registration questions, decides whether the person looks like a high-value guest according to the criteria you describe, and, if so, sends a notification. You hear about an interesting registrant while there is still time to reach out.

It suits community managers, founders hosting dinners and sponsors who want the right people in the room.

What you get out of it

The right guests are noticed
A decision-maker at a target company who registers in the morning can be invited to a private pre-event dinner by afternoon. Without the alert, they would pass through unnoticed. Those relationships often shape the whole event.
Hosts spend time on people, not spreadsheets
Reading every registration answer is slow work. Letting the AI read them all and flag the exceptions leaves you with a short list of people worth a personal message. That frees up time for real conversations.
Sponsors and partners get better introductions
Knowing who is attending lets you introduce sponsors to the people they came to meet. That makes the event more valuable and makes sponsors more likely to return. That makes your next sponsorship conversation easier.
Criteria stay consistent
The same description of a high-value guest is applied to every registrant, so the first and the last are judged by the same standard. Human reviewers tire and apply rules inconsistently.
Capacity decisions improve
For events with limited seats, you can see who deserves one before the event fills up. That helps you manage approvals with a clear idea of who you want to attend.

How it works

What happens, step by step

When a guest registers for one of your Luma events, Luma tells ClickRuntime straight away.
AI reads the guest's registration answers and labels them as an investor, founder, student or other.
If the guest looks like an investor or founder, a message appears in your #events Slack channel with their name, email and answers.
Everyone else is left out, so the channel only shows the guests worth a closer look.

Before it runs live

Connect Luma
Paste your automation's link into the other app's webhook settings

What you get

RunsThe moment it happens

Spot VIP registrants from their answersjust nowSucceeded

Slack · #events⭐ Investor registered for Northwind Demo Night: Alex Kim (alex@acmeventures.com) Role: Partner at Acme Ventures

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.

Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

Changes you can ask for

Act only on the items that match your own rules, and skip the rest
Change what the AI looks for, or how it writes the result
Add another app, for example also send it to Slack
Combine it with other Luma steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.

ai_triage_of_registration_answers.pyexample

from clickruntime import on_event, ai, notify

@on_event
def handle(event):
    body = event.json or {}
    if body.get("type") != "guest.registered":
        return {"skipped": True}
    g = body["data"]
    answers = "\n".join(f"{a.get('label')}: {a.get('value_text') or a.get('answer')}" for a in g.get("registration_answers") or [])
    label = ai.generate(f"Registration answers:\n{answers[:1500]}",
                        system="Classify this person as exactly one word: investor, founder, student or other.",
                        max_output_tokens=5).text.strip().lower()
    if label in ("investor", "founder"):
        notify.slack(f"⭐ {label.title()} registered for {g['event']['name']}: {g.get('user_name')} ({g.get('user_email')})\n{answers}",
                     channel="#events")
    return {"label": label}

FAQ

Common questions

How do I tell it what a high-value guest is?

Describe it in plain language, for example founders of companies with more than 20 staff, or anyone who mentions hiring. The AI applies your description to each set of answers. If the flagged guests are wrong, refine the description.

Does it work if I only ask for name and email?

Not well, because there is nothing to judge. It needs answers to questions like company, job title or goals. If your form is thin, add one or two questions to Luma first, since the quality of the alert depends on the quality of the answers.

Where does the notification go?

To Slack, or by email, depending on your setup. It includes the guest's name, the answers that triggered the flag and the AI's brief reason. That lets you check the decision and decide whether to reach out.

What permissions does it need?

calendar API key. Nothing else in your accounts is used.

Does it need AI?

Yes. It uses ClickRuntime's built-in AI, so you don't need an OpenAI or Anthropic key. Every plan includes a monthly AI allowance.

How many runs does it use?

One run for each event the app sends.

Can I change how it works?

Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

The moment it happens