Use case · Operations
Hand the hard bits to the agent. Then carry on.
An automation can delegate a task to the agent, wait for it to finish and use its result in the next step. A person starts the task first.
Some steps need judgement, like reading a long thread and deciding what to do. A fixed automation can't do that.
The automation does the routine steps and the agent handles the judgement step. You see the agent's result before anything risky happens.
How it works
Set it up once. Let it run.
- 01
Build the automation
Create the routine steps as usual.
- 02
Add "delegate to agent"
Describe the task for the agent.
- 03
Wait for the result
The run waits until a person starts the task and it finishes.
- 04
Use the result
Pass the output to the next step. Risky steps still wait for your approval.
What changes
What you get back
Routine plus judgement
Each does what it is good at.
A person starts it
The task is parked until you pick it up.
Approvals still apply
The agent's danger list is unchanged.
Templates
Copy these workflows
- ai agent
Weekly agent follow-up on quiet deals
Each Monday Montr hands a lead follow-up task to the AI agent. It reads each deal's history, drafts the next touch and waits for your OK before sending.
About 3 hours a week - ai agent
Monday performance review by the agent
Each Monday at 9 the agent reads your analytics, names the strongest and weakest signals, writes a report and proposes next steps for your approval.
About 2 hours a week
Built with
The parts of Montr this uses
FAQ
Questions you might have
Does the agent start by itself?
No. The task is parked until a person starts it.
Put your growth on autopilot. Keep your hand on the wheel.
Join the waitlist. We open Montr BI to teams in India, the US and the GCC in small groups, and we set up your first workflows with you.