Prices are checked against each store and labelled with when.
It checks today's price at every store, compares the alternatives and answers in about a minute.
This is an n8n workflow template that turns a college's WhatsApp number into an AI admissions receptionist. It ingests college documents into a Supabase vector store, then answers student questions in text, voice notes, and images using OpenAI, with a second OpenAI step reviewing each draft reply before it is sent. It suits admissions and IT teams already running n8n, OpenAI, Supabase, and the WhatsApp Business API who want a self-hosted, customizable assistant rather than a closed SaaS chatbot. Against off-the-shelf admissions chatbots, it offers full control over prompts, data, and logging, but you build and maintain the stack yourself.
In stockPriced in GBP (£4.99)
This is an n8n workflow that turns a college admissions WhatsApp number into an AI receptionist. It ingests college documents into a Supabase vector store, then answers student enquiries sent as text, voice notes or images.
When a WhatsApp message arrives, the workflow detects the message type. Voice notes are downloaded and transcribed with OpenAI. Images are downloaded and read with OpenAI Vision, and any image caption is combined with the extracted content. The input is then normalized into a single question, and a conversation record is created in Supabase.
An OpenAI chat agent drafts a reply using the Supabase vector-store retriever to find relevant college information. Chat history is stored in Postgres. A second OpenAI reviewer checks the draft against the same knowledge base. It approves the draft, retries once with correction instructions, or falls back to a safe response. The final reply is sent on WhatsApp and the Supabase conversation record is updated.