The moment it happens

Screen new job applications in Airtable

Each applicant is scored against the job and sorted into shortlist, maybe or reject, and you get an email about the shortlisted ones.

Runs: The moment it happens
Apps: Airtable
AI: Yes, uses the built-in AI allowance
Access: data.records:read, data.records:write

Send this to your assistant

Create a ClickRuntime automation: when someone applies through my form, score their CV text against our Senior Designer job description, classify them as shortlist, maybe or reject with a short reason, save it all to my Airtable Candidates table, and email me the shortlisted ones.

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

A recruiter with 200 applications for one role, or a sales team with a steady flow of inbound leads in an Airtable base, cannot read everything with care. The first ten get a thoughtful look and the rest get a skim. Strong candidates who applied on a Friday are overlooked until the following week, and good leads go cold because nobody could tell the serious buyer from the person fishing for a free quote. Reading each submission against the same criteria takes hours that nobody has.

When a form submission or a new record arrives, ClickRuntime's built-in AI reads it against the criteria you describe, gives it a score and a category, and writes a short reasoning. The score, category and reasoning are saved on the record itself, and anything that lands in your shortlisted category is emailed to you straight away.

It is most useful for small hiring teams, agencies qualifying inbound requests, and community managers sorting event or grant applications.

What you get out of it

Strong candidates are seen first
A shortlisted applicant is emailed to you within moments of applying. Contacting the best people before other employers do is often the difference between hiring them and losing them. Speed here directly affects who accepts your offer.
Every submission is judged against the same criteria
People tire and mood changes across a long pile. The AI applies one written standard to the first and the two-hundredth application, which makes the process more consistent and easier to defend.
The reasoning is stored with the verdict
Because the explanation sits in the record beside the score, you can see why something was ranked high or low, challenge it, and tune the criteria when the AI gets it wrong.
Hours of first-pass reading disappear
Instead of reading every entry, you start with the shortlist and spot-check the rest. A recruiter can spend an afternoon on interviews instead of on a first screening. The saved hours go to conversations with the strongest people.
Hot leads get a faster reply
Inbound buyers who match your ideal profile surface at once, so your first response goes to the one most likely to buy, while interest is still warm. Sales time goes where it earns the most.
A searchable record of why
Views in Airtable can filter by category or score. Later you can review all rejected applications or revisit leads you ranked low but who later became customers, and adjust the prompt.

How it works

What happens, step by step

When a new application or lead arrives in your Airtable table, the automation picks it up.
AI reads it against the job or criteria you set and gives it a score out of 100, plus a shortlist, maybe or reject decision.
The score, decision and a short reason are written back to the record in Airtable.
For each shortlisted person, you get an email with their name, score and why they stand out.

Before it runs live

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

What you get

RunsThe moment it happens

Screen new job applications in Airtablejust nowSucceeded

Email · Shortlisted: Maya Lindqvist (88)8 years designing B2B dashboards at Northwind, led their design system; strong match on Figma and systems work.

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 Airtable 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_screen_new_applications_or_leads.pyexample

from clickruntime import on_event, credentials, http, ai, notify

BASE_ID = "appXXXXXXXXXXXXXX"
JOB = "Senior Designer: 6+ years in product design, strong systems thinking, Figma, B2B SaaS."
SCHEMA = {"type": "object", "properties": {
    "score": {"type": "integer"}, "category": {"enum": ["shortlist", "maybe", "reject"]},
    "reason": {"type": "string"}}, "required": ["score", "category", "reason"]}

@on_event
def handle(event):
    app = event.json or {}
    result = ai.generate(
        f"Job description:\n{JOB}\n\nCV:\n{app.get('cv_text', '')[:6000]}",
        system="Score the candidate 0-100 against the job, classify them and give a one-sentence reason.",
        json_schema=SCHEMA, max_output_tokens=150).json
    http.post(f"https://api.airtable.com/v0/{BASE_ID}/Candidates",
              headers={"Authorization": f"Bearer {credentials.connection('airtable', 'work')}"},
              json={"typecast": True, "records": [{"fields": {
                  "Name": app.get("name"), "Email": app.get("email"), "Score": result["score"],
                  "Category": result["category"], "Reason": result["reason"]}}]}).raise_for_status()
    if result["category"] == "shortlist":
        notify.email_me(f"Shortlisted: {app.get('name')} ({result['score']})", result["reason"])
    return result

FAQ

Common questions

Does the AI make the final decision on candidates?

No. It gives a score, a category and reasoning to help you prioritize, and every record stays in your base for a person to review. For decisions about people, treat the verdict as a first sort, not a ruling.

What fields does the AI read?

Whatever the form or record contains: free-text answers, a pasted cover letter, a company name or a link. You decide which fields are included in the prompt, and you can leave out personal details such as age or photo.

Can I define my own categories and scoring scale?

Yes. You describe categories such as Shortlist, Maybe and Decline, and a scale such as 1 to 10, in the prompt. The values are written into single-select and number fields on the record. Adjust the labels to fit your process, whether you screen jobs, grants or event requests.

What permissions does it need?

data.records:read, data.records:write. 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