The moment it happens

Turn meeting transcripts into summary Docs

A transcript you send becomes a Doc with a summary, decisions and action items.

Runs: The moment it happens
Apps: Google Docs
AI: Yes, uses the built-in AI allowance
Access: read+write

Send this to your assistant

Create a ClickRuntime automation: when I send a meeting transcript to this link, write a summary with decisions and action items, save it as a Google Doc and email me the link.

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 hiring manager runs six interviews in a week and records each. Afterward there are hours of transcript and a debrief meeting where memory, not evidence, decides who goes through. The same happens with client calls: decisions and action items sit buried in a long transcript, and someone has to spend an hour writing the minutes that everyone will skim. The debrief becomes a contest of recollection.

You send the transcript text to a ClickRuntime trigger link. Its built-in AI turns it into a structured summary with key points, decisions and action items for a meeting, or a scorecard for a candidate. A new Google Doc is created with the result and you get an email with the link.

Recruiters, project managers and researchers use it to turn raw conversations into documents they can share.

What you get out of it

Minutes without the hour of writing
The summary and action list are produced from the transcript, ready to review. You check and correct them in minutes, and the meeting record exists the same afternoon, not three days later.
Candidates are compared on the same terms
A scorecard built from each interview uses the same structure for everyone. The debrief starts from comparable notes, which reduces the influence of who you spoke to last or who was most memorable.
Action items have owners and dates
Commitments made in the meeting are extracted and listed, so they do not dissolve into the transcript. Follow-up emails are easier to write when the list already exists. Follow-up emails are easier to write when the list already exists and each commitment has a name next to it.
Decisions are recorded
A clear note of what was decided, and why, helps when a stakeholder later says that was never agreed. The Doc is a shared reference that avoids repeated arguments. The Doc is a shared reference that avoids repeated arguments and protects whoever took the decision.
Sensitive transcripts stay in your Drive
The result is a Google Doc in your own account, where you control sharing. You can limit a candidate scorecard to the hiring panel, and delete it when your retention policy requires.

How it works

What happens, step by step

When a meeting transcript is sent to ClickRuntime, it is received straight away.
AI writes a short overview, the decisions made and the action items with owners and dates.
The summary is saved as a new Google Doc.
You get an email with a link to the Doc.

Before it runs live

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

What you get

RunsThe moment it happens

Turn meeting transcripts into summary Docsjust nowSucceeded

Email · Summary: Acme weeklyhttps://docs.google.com/document/d/1MeEtInG456/edit

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 Google Docs 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.

meeting_or_interview_transcript_to_summary_doc.pyexample

from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from clickruntime import on_event, credentials, ai, notify

@on_event
def handle(event):
    body = event.json or {}
    transcript = (body.get("transcript") or event.body)[:30000]
    summary = ai.generate("Summarise this meeting: a short overview, decisions, and action items with owners and dates.\n"
                          + transcript, max_output_tokens=1200).text
    docs = build("docs", "v1", credentials=Credentials(credentials.connection("google", "work")), cache_discovery=False)
    doc = docs.documents().create(body={"title": body.get("title", "Meeting summary")}).execute()
    docs.documents().batchUpdate(documentId=doc["documentId"], body={"requests": [
        {"insertText": {"location": {"index": 1}, "text": summary}}]}).execute()
    link = f"https://docs.google.com/document/d/{doc['documentId']}/edit"
    notify.email_me(f"Summary: {body.get('title', 'meeting')}", link)
    return {"doc": link}

FAQ

Common questions

What format should the transcript be in?

Plain text works best, whether pasted from a recording tool or exported from a meeting platform. Speaker names and timestamps help the AI attribute points correctly. Very long transcripts are handled in parts so nothing important is truncated.

Can I define what the scorecard should score?

Yes. Give the criteria, such as communication, technical depth and culture fit, and a scale, and the AI scores each with a short justification from the transcript. Treat it as a structured summary of evidence, and keep the hiring decision with people.

Is the summary reliable for decisions about people?

It reflects what the transcript says, but it can misread tone or miss context, so it should support your judgment, not replace it. Always check key quotes against the recording, especially before a hiring decision or a formal record.

What permissions does it need?

read+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 happensAI