The moment it happens

Share a summary of each call logged in Close

Every logged call appears in Slack with the lead, duration and a short summary of the notes.

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

Send this to your assistant

Create a ClickRuntime automation: when a call is logged in Close, post the lead, who made the call, the duration and a 3-bullet AI summary of the call note to #sales-calls.

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

Sales calls pile up faster than anyone can review them. A rep logs a twenty-minute discovery call in Close with a rambling note or a long transcript, the manager is in meetings, and the details that mattered, such as budget, timing and a competitor mention, stay buried. Coaching and follow-up both suffer.

When Close records a new call activity, this fetches the call, has ClickRuntime's built-in AI write a short summary from the note or transcript, and posts that summary to Slack. There is no OpenAI or Anthropic key to set up, and the whole team can read what happened in a few lines.

Sales managers, solutions engineers and customer success leads find it useful for staying close to calls they were not on. Summaries are written from what your reps log in Close, using ClickRuntime's built-in AI, so there is no separate AI account or key to set up before you can use it.

What you get out of it

Know what happened without listening
A three-line summary tells a manager whether a call advanced the deal. Reading it takes seconds, compared with the twenty minutes needed to replay the recording. Managers get the point of a call in the time it takes to read a few sentences, and can ignore calls that need no attention.
Catch buying signals the same day
Details such as a stated budget or a hard deadline are surfaced in the summary. The account executive can act on them while the prospect is still engaged. Specific details such as a budget figure, a decision date or a named competitor are highlighted, and the rep can act on them straight away.
Make coaching easier
Managers can pick calls to discuss by scanning summaries in the channel. Targeted feedback on a specific call is far more useful than general advice at the weekly meeting. Instead of listening to recordings, a manager can pick a handful of summaries and discuss them in a short, useful coaching session.
Keep teammates aligned on an account
When a rep goes on holiday, the colleague covering sees recent call summaries in Slack. They arrive at the next conversation knowing what was already promised. Whoever covers an account during a holiday can read recent summaries in Slack and walk into the next call properly briefed.
Reduce note-taking burden on reps
Reps can log a quick note or paste a transcript and rely on the summary to carry the message to the team, so they spend more time selling and less time writing recaps.

How it works

What happens, step by step

Each time a call is logged in Close, Close tells ClickRuntime straight away.
The automation fetches the call's details: the lead, who made it, how long it lasted and the notes.
AI turns the notes into a few short bullet points.
A message goes to #sales-calls with the lead, caller, duration and the summary.

Before it runs live

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

What you get

RunsThe moment it happens

Share a summary of each call logged in Closejust nowSucceeded

Slack · #sales-callsCall with *Northwind Traders* by Morgan (14 min) • Wants 50 seats from January • Needs SSO • Send pricing by Friday

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 Close 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.

new_call_summary.pyexample

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

API = "https://api.close.com/api/v1"

@on_event
def handle(event):
    ev = (event.json or {}).get("event", {})
    if ev.get("object_type") != "activity.call" or ev.get("action") != "created":
        return {"skipped": ev.get("object_type")}
    auth = (credentials.secret("CLOSE_API_KEY"), "")
    call = http.get(f"{API}/activity/call/{ev['object_id']}/", auth=auth).json()
    lead = http.get(f"{API}/lead/{call['lead_id']}/", auth=auth, params={"_fields": "display_name,html_url"}).json()
    note = (call.get("note") or "").strip()
    summary = ai.generate(f"Call note:\n{note[:4000]}", system="Summarise in exactly 3 short bullets.",
                          max_output_tokens=150).text if note else "No call note."
    minutes = (call.get("duration") or 0) // 60
    notify.slack(f"Call with *{lead['display_name']}* by {call.get('user_name', '-')} ({minutes} min)\n{summary}",
                 channel="#sales-calls")
    return {"call": call["id"]}

FAQ

Common questions

Does it need a call transcript?

It works from the call note or transcript stored on the Close call activity. If a call has neither, there is little to summarise, so the post will be short. Logging a brief note after each call improves the result.

Is the call data sent to an outside AI provider?

The summary step uses ClickRuntime's built-in AI, so you do not provide a separate AI key. Your Close API key is stored as a secret and is not included in the Slack message. Close data is read with your own API key, which is stored as a secret, and the summary is written by ClickRuntime's built-in AI.

Can it summarise only calls above a certain length?

Yes. A filter on call duration can be added so very short calls such as voicemails are skipped. Ask your AI assistant and read the revised flow before approving it. A duration filter would run before the AI step, so voicemails and very short calls are skipped and never summarised at all.

What permissions does it need?

read. 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