Abstract
AI and Large Language Models (LLMs) have sparked major breakthroughs in many industries including software development.
Cody, an AI Assistant created by Sourcegraph, combines the power of these LLMs with the knowledge of your specific codebase to provide you with an unparalleled developer experience. In this talk, we’ll explore how Cody is transforming the software development process.
Cody provides AI-powered autocomplete suggestions, provides conversational code explanations, writes unit tests, performs code smells, and more. It's like having a senior developer advocate pair programming with you. Come learn how you can leverage Cody in your workflow to become a more productive developer.
Sponsored session
Session Sponsored By
Understand, fix, and automate across your codebase with Sourcegraph's code intelligence platform
QCon San Francisco 2023 is a three day conference for senior software engineers, architects and team leads. An international program committee of working engineers selects every session. Patterns and practices, not products and pitches.
Part of the track
Sponsored Solution Track IIFrom the same track
Monday 2 October
10:35 Marina Sponsored Coding With Cody: How AI Is Revolutionizing Software Development Ado Kukic Director of Developer Relations @Sourcegraph AI and Large Language Models (LLMs) have sparked major breakthroughs in many industries including software development. 14:45 Marina Sponsored Exciting Web Ahead with WebGL/WebGPU—Let’s Build a 3D App w/ Three.js Farhad Ghayour Senior Director of Engineering @McKinsey & Company. 15:55 Marina Sponsored Building a DevOps Culture with Site24x7: Collaboration and Accountability Daniel Ceasar Paul Jalathyan Application Performance Management @Zoho Learn how Site24x7 fosters a DevOps culture by providing real-time visibility to development, operations, and other stakeholders, promoting collaboration and accountability. 17:05 Marina Sponsored A More Useful Programming Model Taylor Khan Software Engineer @Temporal The potential failure cases in a distributed system are numerous and hard to predict. Modern software engineering practices rely on a programming model where errors are known in advance or are handled with blanket error handling policies.