Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
1 contribution to AI AgentHQ
AI front desk for a vet clinic (n8n + Claude), plus the bug that humbled me
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? 👇
AI front desk for a vet clinic (n8n + Claude), plus the bug that humbled me
1 like • 5d
Splitting the form workflow from the main pipeline is a good fix. To answer your question, two things I use: 1. Pin data on the trigger so you can rerun the same booking payload without resubmitting the form each time: https://docs.n8n.io/data/data-pinning/ 2. For the classification part, a small test set of tricky requests with the expected result (bird + "wellness exam" should map to the right exam type) that you rerun after every prompt change. n8n's Evaluations feature is built for this: https://docs.n8n.io/advanced-ai/evaluations/overview/ Is Claude picking the exam type from a fixed list, or writing it freely?
1 like • 23h
@Saad Mehmood A fixed list is the right move. If you're using the AI Agent or LLM Chain node, the Structured Output Parser lets you define the exam type as a field in a JSON schema, so the output comes back in the same shape every time instead of free text. I'd also give it an "unclear" option that routes to a human, so an odd request doesn't get forced into the closest exam type. https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparserstructured/
1-1 of 1
John Carlo Caintic
1
3 points to level up
@john-carlo-caintic-5309
I build GHL systems that agencies can white-label: AI receptionists that answer and book 24/7, lead qualification, and quote follow-up.

Active 23h ago
Joined Oct 17, 2026
Butuan City, Phillipines
Powered by