0% found this document useful (0 votes)
13 views2 pages

Automate Lead Qualification with n8n

Uploaded by

cuttycutty69
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
13 views2 pages

Automate Lead Qualification with n8n

Uploaded by

cuttycutty69
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

Assignment

Assignment Overview
This assignment draws from an X client scenario: a B2B SaaS company receives
50-100 lead inquiries daily via email or forms, but manually qualifying them
(e.g., scoring based on intent, budget, and fit) takes 2-3 hours per day. Your task
is to automate this with n8n, incorporating AI for smarter processing.

Resources Required:

● Free n8n account (self-hosted or cloud—your choice).

● Test data: Use this public Google Sheet as a mock "inquiry database"
(columns: Timestamp, Email, Company, Message, Budget
Mentioned?).

● APIs: Free tiers of OpenAI/Groq for LLM, Google Sheets, and Slack (or
email) for notifications.

Problem Statement
Client Context: Imagine a SaaS company selling marketing tools. Leads come in
via a Google Form (simulated by adding rows to the Sheet). The system needs to:

1. Detect new inquiries.

2. Use AI to analyze and score them.

3. Route high-quality leads to sales (e.g., Slack notification).

4. Log everything for reporting.


Core Requirements (Must-Have):

1. Trigger & Data Fetch: Start the workflow on a schedule (every 15 minutes)
or webhook. Pull new rows from the Google Sheet (use the Sheet's
"Timestamp" to filter unseen entries).

2. AI Analysis Node: Use an LLM (e.g., Groq Llama-3 or OpenAI GPT-3.5) to:

○ Classify the lead's intent (e.g., "Demo Request", "Pricing Inquiry",


"General Question").

○ Score the lead (0-10) based on factors like budget mention,


company size hint, and urgency.

○ Extract key details (e.g., contact name, pain points).

○ Prompt example: "Analyze this lead message: [Message]. Output


JSON with:
{intent: str, score: int, key_details: dict}."

3. Branching Logic:

○ If score ≥7: Send a formatted Slack message (or email) to "sales


team" with details.

○ If score <7: Add a note to the Sheet row (e.g., "Low priority - follow
up later").

4. Error Handling: If the LLM call fails (e.g., rate limit), retry once or log to a
"failures" Sheet tab.

5. Logging: Append a summary row to a "Processed Leads" tab in the


same Sheet (include original data + AI outputs).

You might also like