WhatsApp agent with memory

So they don't have torepeat the details.

The customer shares a detail. The agent saves it and can retrieve it in a later inquiry.

Start free See it in action

Requires a plan with Flows, configured connections and a test execution.

A shop team member works on a laptop while a colleague helps a customer.

A task in your business

I'm Ana. My bike is a size M city bike.

PulpoChatReply on WhatsApp

I'm Ana. My bike is a size M city bike.

WhatsAppReceive the detail
SupabaseRead and save memory
WhatsAppReply in the chat

Reply on WhatsApp

Ana, I have your size M city bike noted.

Start from a prepared flow

Adapt connections and data

Test before activating

From the start to the result.

In this example, the detail is saved for a later inquiry from the same contact.

They write again on WhatsApp

WhatsApp agent with memory

I'm Ana. My bike is a size M city bike.

In this example, the detail is saved for a later inquiry from the same contact.

PulpoChatReply on WhatsApp

I'm Ana. My bike is a size M city bike.

WhatsAppReceive the detail
A message arrives at the configured number.
SupabaseRead and save memory
Get Memory and Save Message retain information for the agent.
WhatsAppReply in the chat
The flow sends the agent's reply to the conversation.

Reply on WhatsApp

Ana, I have your size M city bike noted.

Memory gives the agent context. Check what it saves and how it distinguishes each contact.

Explore the template steps

The diagram shows the catalog's nodes and connections. Review their fields and credentials inside the Flows editor.

View the original catalog description

Create a customizable and versatile AI agent chatbot that has memory capacities and remembers previous conversations with customers. Train the AI agent with custom instructions and knowledge base to provide accurate and business-specific responses to customers on WhatsApp.

The flow is prepared. You provide the configuration.

Choose “Use template”
Open Flows in your account and choose this template from the catalog. «AI Agent Chatbot with Memory storage»
Prepare its connections
Complete credentials, data and instructions for your business task.
Test the result
Run a representative case and check each step before activating the flow.

Before you start

A Pulpo account and plan with Flows available.
Supabase and Google Gemini credentials; memory table prepared.
Instructions and rules for saving and retrieving data per contact.

Start free See plans and terms

Before using this template.

What should I check in this flow?

This template stores conversation memory; it does not include a document knowledge base or team handoff by itself.

What happens after I register?

Open Flows and choose “Use template” in the catalog. Registration opens your account; you will still need to configure and test the flow.

Can I change the steps or stop the flow?

You can edit the nodes and deactivate the flow in the editor. Repeat the tests when you change instructions, connections or data.

Can external connections have separate costs?

Yes. AI models and connected services may require their own account, permissions and usage fees. Review each template connection.

Choose the task you need.

See every template