🤖 Score Enriched Leads Before Routing with AI

A new submission is enriched with Apollo, then a named agent scores it and creates a task only for leads that match your ideal customer profile.

UNIT · TASKADE.FLOW5 STEPS

How this flow runs

When

New Submission

Typeform

Then 1

Enrich User Information

Apollo

Then 2

Agent

Lead Qualifier

Ask an agent · Taskade AI

Knows
your ideal customer profile and typical deal sizes
Remembers
which enriched leads became customers

Then 3

Filter

Continue only if the enriched lead matches your ideal customer profile

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 4

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 Apollo automation do?

A new submission is enriched with Apollo, then a named agent scores it and creates a task only for leads that match your ideal customer profile.

What can you do with it?

  • Score against the enriched record, not the form
  • Send only qualified leads to a rep
  • Sharpen the scoring as outcomes come back

The Steps

This automation runs in 5 steps:

  1. When Typeform — New Submission
  2. Then Apollo — Enrich User Information
  3. Then Taskade AI — Ask an agent ("Lead Qualifier")
  4. Then Filter — continue only when the enriched lead matches your ideal customer profile
  5. Then Taskade — Add Task

What makes this different from a Zapier-style flow?

The "Lead Qualifier" step is not a one-off model call. It is a Taskade AI agent that knows your ideal customer profile and typical deal sizes, remembers which enriched leads became customers, 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 protecting rep time. A new submission is enriched with Apollo, then a named agent scores it and creates a task only for leads that match your ideal customer profile.

How do you set it up?

  • Open the "Automations" tab in your workspace.
  • Click ➕ Add automation, then start from scratch.
  • Add the trigger "New Submission" from Typeform.
  • Add the action "Enrich User Information" from Apollo.
  • Add the action "Ask an agent" from Taskade AI. Point it at an agent called "Lead Qualifier".
  • Add a Filter step: Filter — continue only when the enriched lead matches your ideal customer profile.
  • Add the action "Add Task" from Taskade.
  • Connect your Apollo 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