download dots

🤖 Score New Leads From a Sheet with AI

AI reads each new row, scores the lead, and files it as a task with the reasoning attached.

  • Event-triggered
  • 100+ integrations
  • Branching logic
  • Schedule + monitor
UNIT · TASKADE.FLOW4 STEPS

How this flow runs

When

New Row

Google Sheets

Then 1

Agent

Pipeline Scorer

Ask an agent · Taskade AI

Knows
your ICP, deal sizes and the columns in your lead sheet
Remembers
which scored rows actually closed

Then 2

Filter

Continue only if the lead scored high enough to be worth a call

Stop a run cleanly when a condition is not met. A filtered run is not a failure, so it never shows up as an error — inside a loop it skips just that item and keeps going.

Then 3

Add Task

Taskade

This agent carries its knowledge and memory between runs, and can call your other automations as its own tools. How custom agents work

Filter is a step you add in the builder, in the same list as an app step — there is no separate scripting surface. All automation actions

Build this flow with AI

Opens the builder with these steps already described. Free to start, no card.

What does this Google Sheets automation do?

AI reads each new row, scores the lead, and files it as a task with the reasoning attached.

What can you do with it?

  • Rank inbound leads the moment the row lands
  • Keep the scoring reasoning next to the lead, not in someone’s head
  • Route only the leads worth a call

The Steps

This automation runs in 4 steps:

  1. When Google Sheets — New Row
  2. Then Taskade AI — Ask an agent ("Pipeline Scorer")
  3. Then Filter — continue only when the lead scored high enough to be worth a call
  4. Then Taskade — Add Task

What makes this different from a Zapier-style flow?

The "Pipeline Scorer" step is not a one-off model call. It is a Taskade AI agent that knows your ICP, deal sizes and the columns in your lead sheet, remembers which scored rows actually closed, so every run builds on the last one instead of starting from an empty prompt.

A stateless "ask the model" step forgets everything the moment it returns. An agent keeps its knowledge and its memory between runs, carries its own tools, and can be handed work by your other automations.

Who is this automation for?

Built for sales teams collecting leads in a sheet. AI reads each new row, scores the lead, and files it as a task with the reasoning attached.

How do you set it up?

  • Open the "Automations" tab in your workspace.
  • Click ➕ Add automation, then start from scratch.
  • Add the trigger "New Row" from Google Sheets.
  • Add the action "Ask an agent" from Taskade AI. Point it at an agent called "Pipeline Scorer".
  • Add a Filter step: Filter — continue only when the lead scored high enough to be worth a call.
  • Add the action "Add Task" from Taskade.
  • Connect your Google Sheets account when prompted, then enable the toggle in the top-right corner.

Prefer to describe it instead? Click Build this flow with AI above and Taskade wires the trigger, the steps, and the agent for you.

Related from the blog