I built an AI front desk for the Meow Meow Veterinary Hospital competition round. You type what you need in your own words, and it books, cancels or reschedules against a live Google Calendar. Every request is logged to Google Sheets, and it sends a confirmation email. The design rule: the LLM only turns messy text into structured JSON. All the rules and writes are deterministic code. A misread message can cause a question or a refusal, but never a bad booking. The problem I hit: my form test passed, but the public form threw “Workflow could not be started” in a real browser. n8n won’t start a form workflow that also has a Respond to Webhook node. My test went through the API, which skips that check, so it was a false pass. How I solved it: 1. Split it into a form workflow and a main pipeline workflow. 2. The form workflow passes fields to the main one and shows the HTML result. 3. Re-verified it end to end, and wrote the correction into my test report instead of hiding it. Other bugs live testing caught: - The email step crashed after the booking was saved. It used a helper the n8n code sandbox doesn’t have. I made both email steps crash-proof. - “Wellness exam for a bird” booked an Exotic Exam. A prompt fix plus a rule check solved it. What I’m proud of: - 20 of 20 required tests and 14 extra cases passing live - Rollback if the sheet write fails after the calendar event is created - Replay-safe: the same request ID returns the original answer instead of double-booking - Prompt injection and medical-advice requests are refused or handed off Lesson: a test only counts if it uses the same path your users do. Screenshots are attached: the workflow canvas, the form, and the records sheet. Happy to share the structure or prompts if anyone wants them. How do you test your n8n workflows? 👇

Mine is anything with copy paste. invoices, follow up emails, rechecking the same numbers. I finally automated my follow up emails last month and got 3 hours back per week. So what eats your time every week that you still do by hand?

Honest confession from my side. Early on I built 5 workflows for a client in week one. All live, all working. A month later they touched 2. The other 3 sat there and needed babysitting every time a source changed format. Now I do the opposite. Build 2 first, let them run for 2 weeks, then ask what still hurts. Fewer automations, fewer fires, happier client. Have you ever shipped one that nobody used? What happened to it?

This video shows you how to find and verify anyone's work email using Claude and Firecrawl's Alexandria MCP. Instead of paying monthly for tools like Apollo or Hunter separately, this single MCP connection searches over a hundred data providers automatically, moving to the next source when one comes up empty. Check it out! 👇

Wanted to share a win from my latest cold campaign . For a long time, my campaigns struggled. I thought the problem was my email copy or my warmup tool. It wasn't. The problem was the level of leads I was targeting. Most people in AI automation are stuck sending to Level 1 leads. Here is the difference: Level 1: Dead Scrapes (Zero Intent) Scraping 5,000 emails off Apollo or Google Maps by generic title (e.g., "Founder"). You don't know if they have money. You don't know if they have the problem. Result: Low replies, high spam complaints. Level 2: Cleaned Leads (Basic Filters) Verified through Zerobounce / Debounce. Correct headcount and industry. Better deliverability, but you are still just a stranger pitching out of nowhere. Level 3: Signal-Based Leads (Active Intent) This is what produced the numbers in the screenshot. I stopped emailing people based on their job title. I only emailed them if they triggered an active signal: Spend Signal: They are actively spending money on Meta or Google Ads right now (proof they have budget and value customer acquisition). Tech Signal: Specific tools or pixels detected on their site (proof of their exact workflow). Growth Signal: Active hiring or specific changes in their business. Why this changes reply rates: When a lead is Level 3 (Signal-Based), you don't need a 300-word pitch. You don't need fancy AI personalization. You just point out their live signal in the first sentence: "Saw you're running ads for [X] on Meta..." Because the relevance is 100%, the perceived friction drops to zero. They reply because it’s timely, not because of sales hacks. I documented my exact scraping setup, the 3 intent filters I use, and the email sequence inside a Notion doc. I dropped the direct Notion doc link in the first pinned comment below 👇 No pitch, no gate. Take the filters and test them on your own campaigns.