The moment it happens

Get a short summary of every application

Each long application arrives as one paragraph that covers who applied and what stands out.

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

Send this to your assistant

Create a ClickRuntime automation: when someone submits my Tally "Design internship" application, summarise their answers in one paragraph, note their portfolio link, and email it to me.

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 coach, a recruiter or a program manager uses a Tally form with long-form questions: tell us about your business, why do you want this role, describe the problem you are facing. Each response is a page of text. Reading twenty of them in a row is exhausting, and the best candidates are easy to miss when the first few paragraphs all sound alike.

As soon as a Tally form is submitted, ClickRuntime receives it, has ClickRuntime's built-in AI write a one-paragraph summary and, if you want, a score against criteria you describe, then emails you the result. You can decide in thirty seconds whether a response deserves a full read or a quick reply.

It suits application forms, intake questionnaires, discovery calls and any form where answers run long.

What you get out of it

The strongest responses surface first
A score or short rating next to each summary helps you spot standout applicants or promising leads at a glance. Good opportunities do not sit unread at the bottom of a pile.
Triage takes seconds per submission
Reading a paragraph instead of a page lets you sort a full inbox in minutes. You open the long original only for the responses that merit it. A full inbox becomes manageable in one coffee.
Replies can be much faster
When a summary arrives within a minute of submission, you can respond while the person is still thinking about their request. Quick replies correlate with better conversion and happier applicants.
Criteria are applied consistently
The same instructions score every response, which reduces the drift that comes from reading fifty entries while tired. Your own judgment still makes the final call, with a steadier first pass.
The original answers stay intact
The summary supplements the submission and does not replace it. Everything the person wrote remains in Tally, so nothing is lost or distorted by the shortened version. You can always check the summary against the source.

How it works

What happens, step by step

When someone submits an application through your Tally form, it reaches ClickRuntime straight away.
AI reads all of their answers and writes one paragraph on who they are and what stands out.
You get an email with that summary and any links they shared, such as a portfolio.

Before it runs live

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

What you get

RunsThe moment it happens

Get a short summary of every applicationjust nowSucceeded

Email · Design internship: Mei TanThird-year interaction design student with two shipped app redesigns and strong Figma prototyping… Portfolio: https://meitan.example/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 Tally 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_summary_of_each_response.pyexample

import re
from clickruntime import on_event, ai, notify

def fields(payload):
    out = {}
    for f in payload["data"]["fields"]:
        value = f.get("value")
        if f.get("options") and value:
            ids = value if isinstance(value, list) else [value]
            value = ", ".join(o["text"] for o in f["options"] if o["id"] in ids)
        out[f["label"]] = value
    return out

@on_event
def handle(event):
    answers = fields(event.json)
    text = "\n".join(f"{k}: {v}" for k, v in answers.items() if v)
    portfolio = next(iter(re.findall(r"https?://\S+", text)), "none given")
    summary = ai.generate(text[:6000], max_output_tokens=300,
                          system="Summarise this internship application in one paragraph: background, skills, motivation.").text
    name = answers.get("Name") or answers.get("Full name") or "applicant"
    notify.email_me(f"Design internship: {name}", f"{summary}\n\nPortfolio: {portfolio}")
    return {"name": name}

FAQ

Common questions

Can the summary follow a specific format?

Yes. Ask for a format, such as three bullet points, a one-line verdict or a list of red flags, and the AI step follows it. Tell your assistant the layout you prefer and approve the change before it applies.

Does the scoring decide who I accept?

No. A score is a rough first-pass signal based on criteria you describe. It can be wrong, so use it to prioritize your reading, not to reject anyone automatically, and keep a human decision for anything that affects people.

Which Tally fields does the AI see?

It sees the labels and answers from the submission payload. You can restrict it to specific questions, for example leaving out contact details so the summary focuses only on the substance of the answers. Ask for fewer fields if privacy matters.

What permissions does it need?

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