Issue No. 44Week ending Sunday, November 1, 2026759 episodes · 3,334 write-ups
The Podcast Summary.

The best ideas from 30+ top podcasts, every week.

AI agents

Jay Parikh on AI agents

8 quotes from 1 episode on Latent Space, each with a timestamped link to the source.

8 quotes1 episode

The short version

Jay Parikh states that coding agents allow people without software engineering backgrounds to build and share ideas on GitHub. The platform now handles 17.9 billion code pushes for 225 million developers globally.

Most interesting insights

GitHub processes 17.9 billion code pushes, 34.3 billion commits, and 1.3 billion pull requests.

“There's 17.9 billion code pushes. There's 34.3 billion commits. There is um 1.3 billion PRs.”

Jay Parikh, Latent Space · November 2026 · Watch at 4:22 ↗

From Why Agents Break GitHub's Old Architecture

The developer platform serves 225 million accounts across every country globally.

“225 million developers on the platform and that spans every country in the world…”

Jay Parikh, Latent Space · November 2026 · Watch at 4:03 ↗

From Why Agents Break GitHub's Old Architecture

Jay Parikh skips formal pull requests and issue trackers to experiment with autonomous agents in personal repositories.

“There's repos I have that I tinker with and play with…”

Jay Parikh, Latent Space · November 2026 · Watch at 7:38 ↗

From Jay Parikh on Why GitHub Is Rethinking the Pull Request

Top talking points

  1. Coding agents open software creation to non-engineers

    People lacking technical skills can now use AI agents to build and share ideas. Jay Parikh notes GitHub accommodates these new creators alongside teams managing older systems.

    “Now you don't have to be a skilled software engineer to use GitHub, right? So now with coding agents can do a lot of things for you and then you can share an idea.”

    Jay Parikh, Latent Space · November 2026 · Watch at 5:39 ↗

    From Jay Parikh on Why GitHub Is Rethinking the Pull Request

  2. GitHub is rebuilding infrastructure to handle agent activity

    The company is evolving every layer of the technology stack to support AI agents and prevent database failures. Jay Parikh confirms the team plans to complete this infrastructure migration by next year.

    “…how do we keep evolving every layer of the stack that's a theme that has been with us for a while but I think we finally put it together in some way to tell the story from the bottom kind of infrastructury layers all the way up.”

    Jay Parikh, Latent Space · November 2026 · Watch at 19:23 ↗

    From Why Agents Break GitHub's Old Architecture

    “…that's the plan next year next year that's a pretty what we're what we're aiming for right.”

    Jay Parikh, Latent Space · November 2026 · Watch at 19:37 ↗

    From Why Agents Break GitHub's Old Architecture

2 more quotes from Jay Parikh

“Remember across 225 million developers, big enterprises, small, students, etc., we do have to provide a platform with many concepts…”

Jay Parikh, Latent Space · November 2026 · Watch at 7:22 ↗

From Jay Parikh on Why GitHub Is Rethinking the Pull Request

“I think that there's still also a lot of code that exists and you think about all of the code that's been written in Java and .NET that's running business-critical massive businesses today…”

Jay Parikh, Latent Space · November 2026 · Watch at 8:43 ↗

From Jay Parikh on Why GitHub Is Rethinking the Pull Request

Key takeaways from these write-ups

Why Agents Break GitHub's Old Architecture

  • Agents now author about 40% of all pull requests on GitHub, and total agent activity grew six times in just six months.
  • GitHub now serves 225 million developer accounts across the world, adding a new developer every single second in the latest Octoverse report.

Jay Parikh on Why GitHub Is Rethinking the Pull Request

  • Jay Parikh, EVP of CoreAI at Microsoft, skips pull requests and issue trackers entirely when building with autonomous coding agents in his own repositories.
  • GitHub is designing its core building blocks to be configurable, accommodating both solo agent-driven creation and strict enterprise review cycles.

How we attribute quotes. Every quote was matched against the episode transcript, so the words and the timestamp are real (we trim filler words like "um", nothing else). The name comes from our written summary of the episode, and we use it only when a separate check of the captions finds that person on the episode. YouTube gives us no voice-by-voice transcript, so open the timestamp to hear who is talking. See a wrong name? Tell us and we fix or remove it.

More

The Sunday Email

Get next Sunday's issue in your inbox.

The week's best AI, tech, business, science, and culture podcasts in one short read. Free, every Sunday.

You get both newsletters, The Throughline and The Carry. No spam. Unsubscribe with one click.