~/devreads

Swiggy Bytes

https://bytes.swiggy.com/ · 10 posts · history since 2026 · active

29 May

Aishwary Yadav 12 min read

IWTC Introduction If you have ever typed “I want to cancel my order” into a support chat, you were probably not looking for a workflow. You were looking for clarity, speed, and some assurance that the platform understood what had gone wrong. At Swiggy, this seemingly simple interaction sits at the intersection of multiple live systems and stakeholders: a customer…

llm-applicationscustomer-experiencechatbot-developmentai-assistants-chatbotsai

Yash Khandelwal 12 min read

The Problem A Delivery Executive (DE) finishes their day, opens the app, and expects a clear breakdown of what they earned. Instead, they often see a payout that does not fully match their expectations — an incentive missing, a deduction they do not recognise, or a credited amount lower than what they had mentally calculated. At Swiggy, these seemingly simple…

customer-experienceartificial-intelligencelarge-language-modelsagentic-aidata-science

25 May

Aarav Nigam 8 min read

Author: Aarav Nigam Special thanks to Charan and Meghana Negi for their contribution and guidance throughout this project. Introduction Every delivery has a moment where standard navigation stops being useful. Getting from a restaurant or dark store to the customer’s neighborhood is largely a solved problem. Existing routing systems do that well. The harder part begins after the delivery executive…

logisticstechspatialdatasciencemachine-learninglast-mile-deliverygps-trajectory-clustering

Aarav Nigam 7 min read

Authors: Charan , Aarav Nigam Special thanks to Meghana Negi for her contribution and guidance throughout the project. Introduction In hyperlocal delivery, finding a customer’s location is only half the problem. A latitude-longitude pin can tell us where a delivery ends on the map, but not how a delivery partner should interpret that location in the real world. In dense…

point-of-interestdata-engineeringhyperlocal-deliverygeospatial-dataaddress-resolution

15 May

Sahib Majithia 10 min read

Authors : Sahib Majithia Satpalsingh Jaspalsingh Ghunia Mano Ranjith Kumar M Special thanks to Potturi Hemanth Sai Varma and Soumyajyoti Banerjee for their contributions throughout the project and Sunil Rathee for his guidance. Introduction The quick commerce industry has fundamentally redefined consumer expectations — from “delivery in days” to “delivery in minutes.” This shift is not merely an operational upgrade…

llm-for-time-serieshierarchical-modelingquick-commercedemand-forecastingfoundational-model

4 May

Ashoka Chandra Wardhan 11 min read

Picture this: Your favorite batsman is on strike, two runs needed off the last ball — and you’re starving. Do you close the match to open a food app? Of course not. Nobody does. (Blame our laziness 😅) That’s the exact problem Swiggy and JioHotstar set out to solve: let users order food without ever leaving the JioHotstar app. The…

foodswiggy-engineeringweb-development

22 Apr

Bhagi Srinivasu Reddy 15 min read

A while back, a seemingly harmless change to a shared UI library made it all the way to a release demo before anyone noticed that several parts of the product looked… off. Nothing was functionally broken, but a change in a shared package accidentally overwrote some UI colours that were only used in a few places. Since everything was still…

storybookvisual-regression-testingfront-end-developmentplaywright-automationautomation-testing

10 Apr

Ramkishore Saravanan 8 min read

Real-time ML Ranking for Autocomplete: Deploying Learning-to-Rank inside OpenSearch (Part 1) Co-authored with Srinivas Nagamalla . Special mentions to Yawan Gupta and the Search-engineering-team for their contributions. Autocomplete is one of the most latency-sensitive surfaces in any consumer app. At Swiggy, autocomplete is triggered on every keystroke, so ranking has to fit within a tiny latency budget while serving far…

opensearchsearch-auto-completemachine-learninglearning-to-rankswiggy-data-science

26 Mar

Arpit Goel 10 min read

Two tiny AI models. No server. ~300ms. Here’s the story. Authors: Arpit Goel , Shruti Shrivastava The Problem Crew is a conversational concierge — one chat box to book cabs, restaurants, hotels, trips, gifts. No separate screens. Just type what you need. A user types “book cab from airport” and submits. That works well — but a chat box alone…

lmsai-on-deviceaimachine-learningreact-native

24 Mar

anurag shahi 26 min read

The Micro-Frontend Evolution: Why We Traded S3 Behaviors for Module Federation (and What It Cost Us) A practical guide/story from the team that migrated multiple B2B dashboards to a unified Module Federation architecture — including the scariest part: moving thousands of authenticated users to a new domain without a single forced logout. “S3-based micro-frontends are not micro-frontends. They are separate…

micro-frontendsmodule-federationfrontend-architectureweb-developmentjavascript