Restaurant Customer Service Automation
Automates restaurant WhatsApp support by detecting intent to answer menu or hours queries and processing table bookings into a database.
What it does
Get instant answers to your menu questions or table availability directly on WhatsApp without waiting for staff. The system automatically detects your request, books your reservation, and saves your details securely before sending you a confirmation.
Step by step
- Set up a webhook endpoint on your server to receive POST requests from the WhatsApp Business Cloud API.
- Configure the database schema in Postgres with columns for customer phone number, reservation date, time, and party size.
- Implement the logic to parse the incoming JSON payload from WhatsApp and extract the sender's phone number and message text.
Where the LLM does the work
- Prompt the Ollama model to classify the user's intent into categories like 'booking', 'menu_inquiry', or 'general_info'.
- Generate a natural language response for non-booking queries by instructing the LLM to act as a friendly restaurant host.
- Extract specific reservation details (date, time, guests) from unstructured text using the LLM's extraction capabilities.
Watch out for
WhatsApp messages may arrive in multiple parts if they are long so you must concatenate them before sending to the LLM.
Phone number formatting varies by country so normalize all incoming numbers to E.164 format before storing in Postgres.
Webhook verification fails if you do not return the challenge string correctly so implement the exact verification endpoint required by Meta.
Tools that fit
WhatsApp Business Cloud Service Receiving and sending customer messages
Ollama Chat Model LLM Processing intent and generating responses
Postgres Service Storing booking data and conversation history
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 Restaurant Customer Service Automation: Automates restaurant WhatsApp support by detecting intent to answer menu or hours queries and processing table bookings into a database. ## Specification - What it does: Get instant answers to your menu questions or table availability directly on WhatsApp without waiting for staff. The system automatically detects your request, books your reservation, and saves your details securely before sending you a confirmation. - Trigger: Triggered by an event (Event · on new WhatsApp message) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - WhatsApp Business Cloud: Receiving and sending customer messages - Ollama Chat Model: Processing intent and generating responses - Postgres: Storing booking data and conversation history ## Known pitfalls, handle each one explicitly in your implementation 1. WhatsApp messages may arrive in multiple parts if they are long so you must concatenate them before sending to the LLM. 2. Phone number formatting varies by country so normalize all incoming numbers to E.164 format before storing in Postgres. 3. Webhook verification fails if you do not return the challenge string correctly so implement the exact verification endpoint required by Meta. ## Reference implementation https://n8n.io/workflows/5881 (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/restaurant-customer-service-automation/ via usecasesforagents.com
Frequently asked questions
Can I use a different Messaging than WhatsApp?
Yes. WhatsApp is only the example messaging in this recipe. The same flow works with ClickSend API, Discord, Google Chat and LINE Messaging API. Swap the messaging 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
Also fits E-commerce Operator.