Kshitij Works

Independent AI products & engineering.
Gurugram, India.

← All products
Available on GitHub

Restaurant AI Agent Platform

From a guest’s first question to their next order.

A restaurant AI assistant for websites and Telegram. Connect menu discovery, business questions, ordering, and staff support in one conversation.

A connected conversation
A guest starts a conversation WEB / TELEGRAM Restaurant AI Agent Platform Business knowledge RETRIEVE Menu & ordering ACT Staff support HAND OVER
Workflow illustration

Designed for

Restaurants looking to connect customer conversations with their menu, ordering, and support operations.

The workflow

How it works.

  1. 01

    Start a conversation

    Guests ask questions through the website or Telegram, using text or voice in multiple languages.

  2. 02

    Get restaurant answers

    The assistant uses your restaurant’s information to answer questions about opening hours, location, and services.

  3. 03

    Explore the menu

    Guests discover dishes, check prices, and ask about ingredients before choosing what to order.

  4. 04

    Build a basket

    Add dishes, choose sizes and extras, or change quantities through chat. The assistant checks choices against the menu.

  5. 05

    Confirm & check out

    Guests provide delivery, pickup, or dine-in details, review the total, and confirm using your configured payment options.

  6. 06

    Keep staff in the loop

    Staff review conversation history, monitor live chats, and pause the assistant to reply directly when guests need help.

Capabilities

Built for the whole workflow.

Business-specific answers

Published restaurant knowledge informs responses, while live prices come from the menu catalog.

Conversations with context

Persistent chat history and sessions support multi-turn conversations, with intent classification routing requests.

Connected ordering

Menu discovery, cart management, order placement, and order tracking connect the assistant to restaurant workflows.

Human support, included

Live chat monitoring, conversation history, and human-agent takeover share a management dashboard.

Getting started

Run it yourself.

Download or clone the project from GitHub to get started. A deployment needs business knowledge and menu information, channel setup, and ordering integration configuration.

Download on GitHub ↗

For the technically curious

Behind the product

A multi-tenant Django platform uses LangGraph to coordinate conversation workflows, published restaurant knowledge, and validated checkout actions. PostgreSQL stores application data, while Redis and Celery support conversation state and asynchronous message processing.

Read the engineering case study ↗

Let’s talk

A different problem with similar constraints?

I also work with teams on custom AI products, integration, and production engineering.

Get in touch