An AI customer support chatbot for a fictional Nigerian food delivery business, Lagos Fresh Kitchen. It runs on n8n Cloud and uses Claude Haiku 5.5 as the AI model. The workflow is three nodes: a chat trigger receives the customer’s message, an AI Agent processes it, and the Anthropic Chat Model writes the answer.

How it behaves The AI Agent has a system message that sets the rules. It must answer only from the business information, never invent prices, areas, hours or policies, and use a fixed fallback line when the answer isn’t there: “I don’t have enough information to answer that accurately. Please contact our support team.”

The business information it knows

Open Monday to Saturday, 9 AM to 8 PM, closed Sundays

Delivers to Lagos Mainland (Ikeja, Yaba, Surulere, Maryland, Ojota, Gbagada) and Island areas (Victoria Island, Ikoyi, Lekki), not outside Lagos

Delivery takes 30 to 60 minutes, with fees from ₦1,000

Menu of jollof rice, fried rice, rice and stew, pounded yam with egusi, grilled chicken, suya and soft drinks

Payments by card, transfer and cash on delivery

Cancellation allowed before cooking starts

No Sunday orders or Sunday delivery, and no event catering

Refunds, complaints and order status go to support

good work

Your GoHighLevel automations are running right now.

Do you actually know what's in them?

Agencies build workflows fast. A client asks for a follow-up sequence, you duplicate an old one, tweak it, ship it. Six months later there are 125 workflows in the sub-account, half of them drafts nobody remembers, and two with the exact same name, so nobody's sure which one is live.

That's how leads get the same message twice. Or none at all.

So I built Automation Guardian.

It connects to a HighLevel sub-account, reads every workflow, and gives you:

→ A health score for the whole account

→ Findings ranked by severity, most urgent first

→ A plain-English explanation of each issue, written by AI, plus the business impact and how to fix it

→ A shareable audit report you can hand to a client

On a real test account it audited 125 workflows in under a second.

And the part I care about most: it's read-only. It never edits, publishes or deletes anything in your HighLevel account. Tokens are encrypted. You stay in control and make every change yourself.

I'm also honest about what it can't see. When HighLevel doesn't share the data a check needs, the report says "Not checked" instead of pretending it passed.

It's launching on the HighLevel Marketplace soon, with a free plan.

If you run a GHL agency and want early access, comment "AUDIT" or send me a DM. 👇

#GoHighLevel #HighLevel #MarketingAutomation #AgencyOwners #SaaS #BuildInPublic #AI

Reporting "Not checked" instead of a pass is the detail that would make me trust the score. Two workflows with the same name is exactly how double sends happen in email platforms too. Does it flag workflows that share a trigger, even when the names are different?