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.
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.
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.
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.
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.
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 ...
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 ...
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...
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 ...
A set of courses designed to make you a better engineer and excel at your career; no-fluff, pure engineering.
Being a passionate engineer, I love to talk about a wide range of topics, but these are my personal favourites.
Arpit's Newsletter read by 21000+ engineers
Weekly essays on real-world system design, distributed systems, or a deep dive into some super-clever algorithm.
Powered by this tech stack.