How GitHub is rebuilding for Agents 225M developers. 34.3B commits in a year. @github’s agent era i...
How GitHub is rebuilding for Agents
225M developers. 34.3B commits in a year. @github’s agent era is a full-stack rebuild—and @jayparikh, EVP of CoreAI at Microsoft, is leading it.
youtu.be/rSWiNE92xqM
Fresh off his GitHub Universe keynote, Jay goes deep on Copilot Fusion: breaking a task across models to improve quality, cost and speed, and how the harness and model orchestration improve together.
We also get into the infrastructure behind agent-scale GitHub, carrying one session from phone to desktop, and a question every AI engineer should care about: how do you connect token spending to useful work shipped?
Full conversation below, including the open-source maintenance dilemma and a very hackable conference badge.
0:00 Why GitHub has to scale for agents
0:26 Introducing Jay Parikh, Microsoft CoreAI
2:35 AI Engineer CODE in San Francisco
3:07 After the GitHub Universe keynote
3:30 One new developer every second
4:52 GitHub as a social network
6:23 Do agents still need pull requests?
8:03 What counts as code in a repo?
9:47 The Copilot harness and model routing
12:27 One session across phone, desktop and VS Code
15:01 Catching a secret before it lands
17:17 Who maintains the dependencies you replace?
19:10 GitHub in 2027 and the move to Azure
20:51 Token budgets and the value of shipped work
22:36 The programmable Universe badge
More on the next generation of coding agents at AI Engineer CODE, Nov 10–12 in San Francisco: ai.engineer/code
225M developers. 34.3B commits in a year. @github’s agent era is a full-stack rebuild—and @jayparikh, EVP of CoreAI at Microsoft, is leading it.
youtu.be/rSWiNE92xqM
Fresh off his GitHub Universe keynote, Jay goes deep on Copilot Fusion: breaking a task across models to improve quality, cost and speed, and how the harness and model orchestration improve together.
We also get into the infrastructure behind agent-scale GitHub, carrying one session from phone to desktop, and a question every AI engineer should care about: how do you connect token spending to useful work shipped?
Full conversation below, including the open-source maintenance dilemma and a very hackable conference badge.
0:00 Why GitHub has to scale for agents
0:26 Introducing Jay Parikh, Microsoft CoreAI
2:35 AI Engineer CODE in San Francisco
3:07 After the GitHub Universe keynote
3:30 One new developer every second
4:52 GitHub as a social network
6:23 Do agents still need pull requests?
8:03 What counts as code in a repo?
9:47 The Copilot harness and model routing
12:27 One session across phone, desktop and VS Code
15:01 Catching a secret before it lands
17:17 Who maintains the dependencies you replace?
19:10 GitHub in 2027 and the move to Azure
20:51 Token budgets and the value of shipped work
22:36 The programmable Universe badge
More on the next generation of coding agents at AI Engineer CODE, Nov 10–12 in San Francisco: ai.engineer/code
💬4🔄1❤️3👀765📊5