How Swiggy designed and scaled its chatbot

2293 views Backend System Design

Swiggy has automated its customer support with Chatbots; so what’s their architecture? Let’s find out today.

Chatbots are essentially a Decision Tree where nodes are the states the conversation could be in and the edges are conditional statements. Depending on which statement (edge) meets the criteria, the conversation moves forward in that direction.

At each step, Swiggy shows the customer the options which are the child nodes of the current node until all the information is gathered; and the flow stops upon reaching the terminal state.

Key components and architecture

The decision tree is stored in a relational database. It can be generated using historical customer support data and can be updated by product and business teams.

The core chatbot service needs to access data from other services/databases like Payments, Orders, and Notifications. Accessing peripheral information will provide a rich experience to the users.

The most important part chatbot is to interact with the Fraud Detection system. Given that the entire flow is automated and needs no manual intervention, the chances of Fraud shoot up.

Fraud Detection System, in real-time, would see if the customer is trying to commit fraud. This system would interact with historical information about the customer, past refunds, image processing, and much more.

There may be a possibility that the customer still needs to talk to an executive hence the customer support executive needs to get all of this information, including fraud probability, in an easy-to-use dashboard.

Hence, a real-time pipeline would be needed to ingest and move data across all of these systems. Apache Spark is an excellent candidate for building this.

Business Continuity Plan

If the Chatbot is down, then Swiggy switches to a simple chat interface that connects directly to an executive, continuing to service the end users.

Key Metric

A metric that Swiggy chases is Bot Efficacy which is nothing but the percentage of requests handled by the bot vs executive. Swiggy wants to handle as many requests as possible through the bots as it would help them remain efficient at scale.

Arpit Bhayani

Arpit's Newsletter

CS newsletter for the curious engineers

❤️ by 21000+ readers

If you like what you read subscribe you can always subscribe to my newsletter and get the post delivered straight to your inbox. I write essays on various engineering topics and share it through my weekly newsletter.

Other essays that you might like

Overview of Discord's data platform that daily processes petabytes of data and trillion points

924 views 54 likes 2022-11-14

When a company scales, they adopt microservices and each service typically gets its own independent database. With data ...

How Airbnb designed and scaled its central authorization system - Himeji

2206 views 98 likes 2022-11-07

Authorization plays a critical role in ensuring that the platform is not abused. For example, Instagram ensures that if ...

How Gojek masks and keeps users' phone numbers secure at scale?

2572 views 152 likes 2022-10-31

Do hyperlocal companies like Uber, Ola, Swiggy, Gojek, Zomato, etc share our phone numbers with the delivery people or t...

The architecture of Yelp's in-house Search Engine - nrtSearch

2193 views 81 likes 2022-10-24

Elasticsearch is a great search engine, but Yelp was not happy with its performance, so they built their own HTTP layer ...

Be a better engineer

A set of courses designed to make you a better engineer and excel at your career; no-fluff, pure engineering.

Paid Courses

System Design Masterclass

A masterclass that helps you become great at designing scalable, fault-tolerant, and highly available systems.

1000+ learners

Details →

Redis Internals

Learn internals of Redis by re-implementing some of the core features in Golang.

28+ learners

Details →

Free Courses

Designing Microservices

A free playlist to help you understand Microservices and their high-level patterns in depth.

17+ learners

Details →

GitHub Outage Dissections

A free playlist to help you learn core engineering from outages that happened at GitHub.

67+ learners

Details →

Hash Table Internals

A free playlist to help you understand the internal workings and construction of Hash Tables.

25+ learners

Details →

BitTorrent Internals

A free playlist to help you understand the algorithms and strategies that power P2P networks and BitTorrent.

42+ learners

Details →

Topics I talk about

Being a passionate engineer, I love to talk about a wide range of topics, but these are my personal favourites.

  • v13.7.5
  • © Arpit Bhayani, 2022

Powered by this tech stack.