Designing for Intelligence at GitHub Next: Patterns & Practices for Making AI powered Products

ABOUT THE TALK:
What does it take to design successful products around AI capabilities? Achieving acceptable reliability is often not about model improvements and fine-tuning. A holistic approach to building AI-powered products requires thinking about how we elicit context from users, how we prompt the models, how we decide to measure the goodness of results, and how the interaction models we use weave intelligence into experiences.

GitHub Next is the birthplace of products like GitHub Copilot and is currently exploring the frontiers of AI assistance for the entire software development lifecycle. In this talk, Idan Gazit shares some practical learnings from experience building and shipping these prototypes and successful interactions with the broader business.

ABOUT THE SPEAKER:
Idan Gazit is a Senior Director of Research at GitHub Next, leading the Developer Experiences team. He is a hybrid designer-developer, and can usually be found geeking out about the Web, data visualization, typography, and color. He lives in the East Bay with his family and surrounds himself with a rotating cast of half-finished projects.

ABOUT DATA COUNCIL:
Data Council (https://www.datacouncil.ai/) is a community and conference series that provides data professionals with the learning and networking opportunities they need to grow their careers.

Make sure to subscribe to our channel for the most up-to-date talks from technical professionals on data related topics including data infrastructure, data engineering, ML systems, analytics and AI from top startups and tech companies.

FOLLOW DATA COUNCIL:
Twitter: https://twitter.com/DataCouncilAI
LinkedIn: https://www.linkedin.com/company/datacouncil-ai/

Видео Designing for Intelligence at GitHub Next: Patterns & Practices for Making AI powered Products канала Data Council