Deals going dark
A deal rarely dies loudly. It goes quiet. The agent notices the silence inside your risk window, explains what it is seeing, and puts a follow-up in front of the owner before the quarter does.
The brief
Written like you’d brief a person.
This is the whole setup - a procedure in plain language, with tools and specialist agents referenced inline. When it runs is not written here: that’s the trigger, configured beside it.
For each open deal from #yekar.hubspot.search-records, check the last touch with #yekar.hubspot.list-record-activity, #yekar.gmail.search-messages and #yekar.google-calendar.list-events. When nothing has moved inside the risk window, explain the evidence, draft a follow-up with #yekar.gmail.create-draft, and alert the owner with #yekar.slack.send-message.
How it runs
From trigger to logged outcome.
Trigger
Schedule - A daily check of open deals against your configured risk window
Monitor the pipeline
Reads every open deal and the last touch on each channel.
Detect the gap
Flags deals with no meaningful email, meeting or reply inside the window.
Retrieve the context
Pulls the thread, the stakeholders, and where the deal was heading.
Explain the risk
States what it saw and did not see - evidence, not a score.
Draft the follow-up
Proposes the next-best message for the owner to send.
Where people stay in control
Nothing consequential runs on its own.
- Outreach is drafted for the deal owner, who decides whether it goes.
- Risk thresholds are yours to set per stage - the agent flags, it never re-stages a deal.
Tools it uses
Runs on accounts you already have.
HubSpot
Gmail
Google Calendar
Slack
Connected once, governed per agent - this use case gets only the tools listed here.
Illustrative savings
$600–$1,600 / month
Assumes 80–250 open deals reviewed weekly by hand at 3–5 minutes each, with the agent doing the first pass daily.
Illustrative monthly savings, estimated from typical handling time at public salary benchmarks, reviewed August 2026. Not a promise or a guarantee - your numbers depend on volume and process.
What makes this dependable
Start with the job
See how Yekar.AI would run one of your real processes.
Bring the job, the systems it touches, and the decisions that need a person.