Skip to content

Weekly

Get next steps for deals that went quiet

Every Monday, deals untouched for 14 days come with a suggested action in Slack.

Runs
Weekly
Apps
Zoho CRM
AI
Yes, uses the built-in AI allowance
Access
ZohoCRM.modules.deals.READ

Send this to your assistant

Create a ClickRuntime automation: every Monday at 9am, find open Zoho CRM deals not modified in 14 days, suggest one next step for each from its stage and notes, and post them to #sales in Slack.

Paste it into your assistant. It tells you what it will send or change before it runs live.

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A sales manager reviews the pipeline in a Friday meeting and finds a $60,000 deal that has not changed in five weeks. The rep says it is still alive, but there is no logged activity and no next step. Across 40 open deals, a handful are drifting like this at any time, and nobody notices until quarter end when the forecast misses.

Every week, open deals in Zoho CRM whose Modified_Time is older than 14 days are retrieved with a COQL query. The built-in AI reads each deal's stage, amount and notes, then suggests a concrete next action, such as a call, a proposal revision or closing it as lost. The result is posted to Slack for the team.

Valuable for managers who coach reps on pipeline hygiene. Managers who run a pipeline review each week can paste the post straight into the meeting notes.

What you get out of it

  • Forecasts reflect reality

    Deals with no movement in two weeks are less likely to close. Flagging them lets you weigh the forecast honestly before the quarter ends, not after the number has been missed.

  • Reps get a specific nudge

    A suggested next step, such as sending revised pricing to the finance contact, is more useful than a message saying the deal is stale. Reps get something to do, not a reprimand.

  • Pipeline review takes less time

    The meeting starts from a short list of deals at risk instead of a scroll through every record. Discussion goes to decisions, and the hour is spent on the deals that need help.

  • Dead deals leave the pipeline

    Some stale deals should be closed as lost. Naming them keeps the pipeline from being padded with opportunities nobody is working, which makes coverage ratios honest. Dead pipeline weighs on forecasts.

  • Revenue at risk is quantified

    The post can include the deal amount, so you see how much value is sitting idle. That makes the case for acting this week, not hoping for a reply that never comes.

  • Coaching with specifics

    A manager can open a one-to-one with a named deal, its age and a proposed action. Coaching becomes concrete, and reps see that stale deals will be noticed. Pipeline hygiene becomes routine.

How it works

What happens, step by step

  1. Every Monday ClickRuntime finds the open Zoho CRM deals that haven't changed in 14 days or more.

  2. AI reads each deal's name, stage and description and suggests one concrete next step.

  3. The list goes to your #sales Slack channel, with each deal's owner, stage and the suggested action.

Before it runs live

  • Connect Zoho CRM

What you get

RunsWeekly
Get next steps for deals that went quiettoday, 9:00Succeeded
Slack · #salesDeals untouched for 14+ days: *Acme expansion* (Alex Kim, Negotiation): send the revised quote with the 3-year option

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

  • Run it at a different time, more or less often, or only on weekdays
  • 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 Zoho CRM 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_stale_deal_triage.pyexample
from datetime import datetime, timedelta, timezone
from clickruntime import on_trigger, credentials, http, ai, notify

@on_trigger
def run(event):
    cutoff = (datetime.now(timezone.utc) - timedelta(days=14)).strftime("%Y-%m-%dT%H:%M:%S+00:00")
    query = ("select Deal_Name, Stage, Amount, Description, Owner.full_name from Deals "
             f"where Modified_Time < '{cutoff}' and Stage not in ('Closed Won', 'Closed Lost') limit 50")
    r = http.post("https://www.zohoapis.com/crm/v8/coql", json={"select_query": query},
                  headers={"Authorization": f"Zoho-oauthtoken {credentials.connection('zoho', 'work')}"})
    deals = r.json()["data"] if r.status_code == 200 else []
    if not deals:
        return {"stale": 0}
    numbered = "\n".join(f"{i + 1}. {d['Deal_Name']} | {d['Stage']} | {(d.get('Description') or '')[:300]}"
                         for i, d in enumerate(deals))
    advice = ai.generate(f"For each stale deal, suggest one concrete next step. Answer as numbered lines.\n{numbered}",
                         max_output_tokens=60 * len(deals)).text.splitlines()
    lines = [f"*{d['Deal_Name']}* ({d['Owner.full_name']}, {d['Stage']}): {a.split('. ', 1)[-1]}"
             for d, a in zip(deals, [x for x in advice if x.strip()])]
    notify.slack("Deals untouched for 14+ days:\n" + "\n".join(lines), channel="#sales")
    return {"stale": len(deals)}

FAQ

Common questions

What does stale mean here?
A deal counts as stale if it is open and its last modification is more than 14 days old. You can change the number of days or add a minimum amount so only larger deals are posted.
Does the AI see my notes and emails?
It uses the deal fields and notes included in the query, such as stage, amount and recent notes. It does not read mailbox content unless that data is logged against the deal in Zoho CRM. Suggestions are advice only, and nothing in Zoho CRM changes.
Are suggestions applied to the deal automatically?
No. The AI's suggestions are posted for people to read. Nothing in Zoho CRM is changed by this step, so reps decide whether and how to act. Only deals above a chosen amount can be included.
What permissions does it need?
ZohoCRM.modules.deals.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 each time it runs (weekly). Checks that find nothing to do and stop right away aren't counted.
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.

Set up “Get next steps for deals that went quiet” from your assistant

Copy the prompt above, or connect your assistant first. Free plan, no credit card.