Lead Scoring & Auto-Assignment
New GoHighLevel contact? GPT-4 scores it 1-100, tags the lead, assigns a rep, and pings Slack for hot prospects.
What it does
Get new leads routed instantly: GPT-4 analyzes your contact's data to score them 1, 100, tags their status in GoHighLevel, assigns the right rep, and alerts you on Slack for hot prospects.
Step by step
- Configure the GoHighLevel webhook to trigger on new contact creation.
- Set up the OpenAI API key and define the JSON schema for the scoring response.
- Map the GPT-4 output categories (Hot, Warm, Cold) to specific GoHighLevel tags.
- Create a Slack channel integration with a predefined message template for notifications.
Where the LLM does the work
- Craft the system prompt that instructs GPT-4 to evaluate engagement signals like email opens and page visits.
- Define the few-shot examples in the prompt to ensure consistent scoring logic across different lead profiles.
- Refine the output parsing logic if GPT-4 returns non-standard JSON structures during initial testing.
Watch out for
GoHighLevel tag names are case-sensitive and must match exactly, verify the spelling of tags before mapping them in the workflow.
Tools that fit
The agent brief
Everything your agent needs, including the gotchas. Copy it and go.
You are helping me build the following AI agent workflow. ## Goal Lead Scoring & Auto-Assignment: New GoHighLevel contact? GPT-4 scores it 1-100, tags the lead, assigns a rep, and pings Slack for hot prospects. ## Specification - What it does: Get new leads routed instantly: GPT-4 analyzes your contact's data to score them 1, 100, tags their status in GoHighLevel, assigns the right rep, and alerts you on Slack for hot prospects. - Trigger: Triggered by an event (Event · on new contact in GoHighLevel) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - GoHighLevel: Contact management and lead assignment - OpenAI: Lead scoring and categorization via GPT-4 - Slack: Alerting on hot leads ## Known pitfalls, handle each one explicitly in your implementation 1. GoHighLevel tag names are case-sensitive and must match exactly, verify the spelling of tags before mapping them in the workflow. ## Reference implementation https://n8n.io/workflows/11408 (workflow template) Fetch and inspect this before building. If it matches my stack, adapt it; if not, rebuild the pattern with my tools. ## Process requirements 1. Before building: ask me which of the listed tools I actually use and what my platform is (n8n / Make / code / other). Do not assume. 2. Adapt the pattern to my answers; do not force the reference stack. 3. Address every pitfall above; tell me how you handled each. 4. Provide a test plan I can run before letting this touch real data. 5. Ask before any step that sends messages, modifies data, or spends money. Source: https://usecasesforagents.com/use-case/lead-scoring-auto-assignment/ via usecasesforagents.com
Frequently asked questions
Can I use a different CRM than GoHighLevel?
Yes. GoHighLevel is only the example CRM in this recipe. The same flow works with Agile CRM, Attio, Close CRM and Freshworks CRM. Swap the CRM connection and keep the rest of the setup as written.
Want this running in your business?
This is what I do. I design and build AI agents like this one, and keep them running. If you want it set up for your team instead of doing it yourself, get in touch.
Who it's for
Built for sales teams who want the prep work done before they pick up the phone.