Software Engineering Daily

Uber’s On-Call Copilot with Paarth Chothani and Eduards Sidorovics

Apr 8, 2025

Paarth Chothani, a Staff Software Engineer at Uber AI, and Eduards Sidorovics, a Senior Software Engineer with a focus on machine learning, dive into the creation of Genie, Uber's AI-powered on-call copilot. They discuss how Genie streamlines incident resolution and enhances team collaboration. The duo sheds light on challenges like knowledge management and user feedback in AI development. They also explore the impact of advanced language models on productivity, emphasizing the need for flexibility in evolving AI applications.

44:21

Creator website

Episode guests

Eduards Sidorovics

Paarth Chothani

AI Summary

AI Chapters

Episode notes

Podcast summary created with Snipd AI

Quick takeaways

Uber developed Genie, an AI-powered on-call copilot, to enhance on-call operations by automating responses and improving incident resolution efficiency.

The architecture of Genie includes a robust filtering system for sensitive data, ensuring compliance while efficiently integrating user-specified knowledge sources.

Deep dives

Challenges Behind Genie’s Development

Uber's team identified a common challenge among engineers related to the inefficiencies of on-call operations and support systems. As engineers frequently sought help in various forums like Slack, there was a notable pain point in accessing accurate and timely support due to fragmented information. This realization drove the inception of Genie, aiming to automate responses and streamline incident resolution by connecting engineers with internal knowledge sources. By creating a solution that could efficiently answer questions and enhance productivity across numerous teams, Uber sought to address a pressing issue that many large organizations face.

Intro

2min

Building Genie: Optimizing Knowledge Management at Uber

16min

Enhancing Documentation and User Experience through AI Feedback Loops

6min

Navigating Customer Feedback and Data Security in AI Development

6min

Navigating the Challenges of Scalable Machine Learning Applications

6min

Advancements in Language Models and AI Innovation

9min

At Uber, there are many platform teams supporting engineers across the company, and maintaining robust on-call operations is crucial to keeping services functioning smoothly. The prospect of enhancing the efficiency of these engineering teams motivated Uber to create Genie, which is an AI-powered on-call copilot. Genie assists with on-call management by providing real-time responses to queries, streamlining incident resolution, and facilitating team collaboration.

Paarth Chothani is a Staff Software Engineer on the Uber AI Gen AI team. Eduards Sidorovics is a Senior Software Engineer on the Uber AI Platform team. In this episode they join the show with Sean Falconer to talk about the challenges that motivated the creation of Uber Genie, the architecture of Genie, and more.

Sean’s been an academic, startup founder, and Googler. He has published works covering a wide range of topics from AI to quantum computing. Currently, Sean is an AI Entrepreneur in Residence at Confluent where he works on AI strategy and thought leadership. You can connect with Sean on LinkedIn.