crmIQ - Store Clients in PostgreSQL

Introduction

This guide walks you through setting up and running the crmIQ - Store Clients in PostgreSQL workflow. This use case provides an automated pipeline that receives inbound client, contact, and meeting payloads via a Webhook (e.g., from LibreChat), maps them into cascading relational tables inside a PostgreSQL database, and triggers parallel autonomous AI Research Agents to enrich your records with deep corporate profiles, stakeholder insights, and interaction sentiment tracking.

Note that this is a Use Case Instruction, you can use this Use Case as an example to build your own custom CRM Ingestion and Enrichment Workflow in n8n.

---

Prerequisites

Check out Connecting n8n Workflows to OpenWebUI via Function to connect OpenWebUI to n8n. You need to have set this up before starting this tutorial. Additionally, you will need:

• An active PostgreSQL database instance with admin privileges.
• OpenAI API or a LiteLLM gateway credential hooked into your n8n workspace.
• Check out Connecting n8n Workflows to OpenWebUI via Function to connect OpenWebUI to n8n. You need to have set this up before starting this tutorial.

---

Steps

Step 1: Open the Workflow

1. On the Use Cases Page find the column crmIQ - Store Clients in PostgreSQL. Now, press the Download icon.
2. Open n8n in you Dashboard and create a workflow. Click on the three dots in the right corner of your screen and then on Import from URL....

1. Enter the URL in the pop-up that appears.

1. Click on Import and the Demo Workflow will appear on your page.
2. Follow the Setup in the Workflow.

---

Step 2: Create a Table

In the n8n application canvas, locate the section labeled Postgres Database Maintenance.

Double-click the node Create Table and execute it. This script establishes your core relational database architecture, incorporating constraints, primary UUID keys, and flexible JSONB properties to house downstream AI enrichments:

SQL

-- CREATE COMPANIES TABLE
CREATE TABLE crm_companies (
    id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
    name VARCHAR(255) NOT NULL UNIQUE,          -- Unique constraint so AI can 'Upsert' on name
    website VARCHAR(255),
    created_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
    updated_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
    ai_research_enrichment JSONB DEFAULT '{}'::jsonb  -- Flexible storage for your Research Agent
);

-- CREATE CONTACTS TABLE
CREATE TABLE crm_contacts (
    id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
    company_id UUID REFERENCES crm_companies(id) ON DELETE CASCADE, 
    first_name VARCHAR(100),
    last_name VARCHAR(100) NOT NULL,
    email VARCHAR(255) NOT NULL UNIQUE,         -- Unique constraint so AI can 'Upsert' on email
    phone VARCHAR(50),
    job_title VARCHAR(150),
    created_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
    ai_profile_enrichment JSONB DEFAULT '{}'::jsonb   
);

---

Step 3: Initialize Inbound Webhook Listening

Navigate to the section titled Webhook Trigger (OpenWebUI).

1. Open the Webhook node. It is preconfigured to listen for a POST request on the path librechat-mcp.
2. Copy the Production URL from this node.
3. Paste this endpoint directly into your OpenWebUI Pipe Function configuration settings (n8n_url) to securely funnel conversational payloads into the extraction pipeline.

---

Step 4: Configure Storage Engine & Relational Mapping

Locate the canvas block labeled Store Information. This module processes entities sequentially using cascading relationships to enforce clean data structures.

1. Insert or Update 'crm_companies': This node maps incoming organizational names and domains, applying an Upsert rule anchored to the name column.
2. Insert or Update 'crm_contacts': Maps stakeholder records using email as the matching constraint while automatically binding the correct parent company_id from the prior node.
3. Insert 'crm_interactions' & 'crm_tasks': Automatically records meeting logs and logs outstanding actions or filters. Double-click these nodes to verify that variable paths correctly intercept your inbound text arrays:

   JavaScript

   // Evaluates incoming array payloads for operational context matching
   "due_date": "={{ $('Webhook').item.json.body.tasks[0].due_date }}"

---

Step 5: Validate Mutation Handlers & Autonomous Research

Move over to the parallel blocks running along the right side of the canvas. Once data fields are stored, the workflow forks into three distinct AI Agents:

• Company Research Agent: Uses your attached chat model to research the corporate entity using its name and website variables.
• Person Research Agent: Evaluates job titles to determine seniority levels, key executive focus regions, and tailor highly optimized sales hooks.
• Relationship Research Agent: Acts as an unstructured conversational text parser. It isolates emotional sentiment profiles and spots named competitors or friction patterns.

Review how each block requires its returned structured information to strip out accidental markdown tags. Open the data update nodes to review the JSON parameters:

JavaScript

// Automatically sanitizes LLM output strings to parse clean JSON objects
{{ typeof $json.output === 'string' ? ($json.output.includes('```json') ? JSON.parse($json.output.split('```json')[1].split('```')[0].trim()) : JSON.parse($json.output)) : $json.output }}

---

Step 6: Deploy Language Models & Enrichment Injection

Within the core intelligence block, link up your active model parameters.

1. Double-click OpenAI Chat Model 1, 2, and 3.
2. Attach your specific AI provider API credentials (e.g., your GLBNXT LiteLLM or OpenAI instance).
3. Confirm the target engine parameter is locked at exactly gpt-4.1 (or your preferred core LLM engine).
4. The Update database layers will automatically catch these evaluated payloads and dump them directly into the target ai_research_enrichment, ai_profile_enrichment, and ai_extracted_entities JSONB columns.

---

Step 7: Manage Database State & Housekeeping

To audit your workflow output during deployment, return to the Postgres Database Maintenance zone.

• View Tables Node: Execute this node to verify running tracking statistics by viewing raw logs straight from your relational rows.
• Truncate Tables Node: During staging, manually trigger this block to cleanly reset all tracking rows and clear testing data without breaking database schemas:

  SQL

  TRUNCATE TABLE crm_companies, crm_contacts, crm_interactions, crm_tasks RESTART IDENTITY CASCADE;

---

Need help? Contact the GLBNXT support team or ask a GLBNXT agent to walk you through the setup.