The moment it happens

Score and flag incoming leads and requests

Each submission gets a score, a category and any risks noted, and the urgent ones land in your inbox.

Runs: The moment it happens
Apps: Groq
AI: Not needed
Access: API key

Send this to your assistant

Create a ClickRuntime automation: give me a link my contact form can post to. Have Llama 3.3 on Groq score each lead from 1 to 10, categorise it as sales, support or partnership, flag anything that matches my blocklist, reply with JSON and email me anything scoring 8 or more.

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

Anything that arrives through a public form tends to need the same first read: is this a real lead, a spam submission, an urgent complaint, a job ad worth a look? A founder with a contact form, a recruiter with an applications inbox or a community manager with a report link spends the first part of every day sorting before doing any actual work. Urgent items are often buried under noise from the same form.

You get a link that accepts text. Each submission is checked against your stored keyword rules, then passed to a Llama model on Groq that returns a structured verdict: a score, a category and a short reason. The result is returned to the sender, and anything high-priority is emailed to you straight away.

It suits lead qualification, report triage, job ad screening and any stream of text where the first decision follows a pattern.

What you get out of it

Urgent items reach you first
High-priority submissions are emailed immediately, so a hot lead or serious report does not wait behind a pile of low-value messages until you get to the inbox. Every minute saved on a good lead can increase the chance of winning it.
Spam and noise filtered at the door
Submissions that fail your rules or score low can be handled differently. You spend your attention on the items that justify it. Rejected items can still be kept for review, so nothing useful is permanently lost to a mistaken filter, and the inbox stays focused.
Consistent judgment every time
The same rules and model apply to every message, so a Friday evening submission is treated like a Monday morning one, with no tired shortcuts. Humans vary through the week, while a rule plus a model stays steady, which is what you want for a first screen.
Structured output you can use
A score and category per submission give you something to sort and filter by, rather than a wall of text you have to interpret. Categories such as lead, complaint and spam can drive routing, so the right person sees each kind, with a short reason attached.
Fast enough to respond live
Groq's quick responses mean the sender can get an answer in the same web request, which suits chat-like flows and instant acknowledgments. That suits embedded forms and chat widgets, where a visitor expects a reply while still on the page.

How it works

What happens, step by step

When a lead or request is sent to your personal ClickRuntime link, the automation starts straight away.
ClickRuntime checks it against your list of blocked words.
A Llama model on Groq scores it from 1 to 10, puts it in sales, support or partnership, and gives a reason.
If it scores 8 or more and contains no blocked words, you get an email with the score, category, reason and the full submission.

Before it runs live

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

What you get

RunsThe moment it happens

Score and flag incoming leads and requestsjust nowSucceeded

Email · Hot leadsHot lead (9/10, sales): 200-seat team at Northwind asking for a demo this month.

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
Add an AI step, for example to summarize, sort or draft a reply
Add another app, for example also send it to Slack
Combine it with other Groq 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.

screen_and_triage_submitted_text_with_a_llama_model_on_groq.pyexample

import json
from clickruntime import on_event, credentials, notify, http, state

@on_event
def handle(event):
    lead = event.json or {}
    text = json.dumps(lead)
    blocked = [w for w in state.get("blocklist") or [] if w.lower() in text.lower()]
    resp = http.post("https://api.groq.com/openai/v1/chat/completions",
                     headers={"Authorization": f"Bearer {credentials.secret('GROQ_API_KEY')}"},
                     json={"model": "llama-3.3-70b-versatile", "response_format": {"type": "json_object"},
                           "messages": [{"role": "user", "content": "Score this lead 1-10 and categorise it as "
                                         "sales, support or partnership. Reply as JSON with score, category, "
                                         f"reason.\n\n{text}"}]})
    resp.raise_for_status()
    result = json.loads(resp.json()["choices"][0]["message"]["content"])
    result["blocked"] = blocked
    if result["score"] >= 8 and not blocked:
        notify.email_me(f"Hot lead ({result['score']}/10, {result['category']})", f"{result['reason']}\n\n{text}")
    return result

FAQ

Common questions

What kind of text can I send to be screened?

Plain text in a web request, for example a form submission, a pasted job ad or a customer report. The text is the thing that is scored, so include everything relevant in one request. Short, clear submissions generally give the best classifications.

How do keyword rules and the AI work together?

Your stored list is applied first, for example always flag mentions of legal action. The Llama model then scores the rest. Combining a fixed rule with the model gives you predictable handling of the cases that matter most.

How accurate is the AI verdict?

It is a first filter, not a final decision. Clear cases are usually classified well, while borderline ones can be wrong, so keep a human check on anything consequential and use the reason text to review it.

What permissions does it need?

API key. Nothing else in your accounts is used.

Does it need AI?

No. It runs without AI, so it doesn't use your plan's 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.

Daily