Devcon Archive logo
Devcon Devconnect Forum Blog
  • Watch
  • Event
    Event: background logo
    • Devcon 7
    • Devcon 6
    • Devcon 5
    • Devcon 4
    • Devcon 3
    • Devcon 2
    • Devcon 1
    • Devcon 0
    • Devconnect ARG
  • Categories
    Categories: background logo
    • Cryptoeconomics
    • Devcon
    • Developer Experience
    • Coordination
    • Core Protocol
    • Layer 2s
    • Real World Ethereum
    • Cypherpunk & Privacy
    • Security
    • Applied Cryptography
    • Usability
  • Playlists

Suggested

Loading results..

View all

About Devcon —

Devcon is the Ethereum conference for developers, researchers, thinkers, and makers.

An intensive introduction for new Ethereum explorers, a global family reunion for those already a part of our ecosystem, and a source of energy and creativity for all.

  • Watch
  • Devcon
  • Devconnect
  • Forum
  • Blog

Get in touch

devcon@ethereum.org

Subscribe to our newsletter

Crafted with passion ❤️ at the Ethereum Foundation

© 2026 — Ethereum Foundation. All Rights Reserved.

devcon8 / ai can write the patch can you get it merged

  • YouTube
AI Can Write the Patch — Can You Get It Merged? preview
  • Details

AI Can Write the Patch — Can You Get It Merged?

Duration: NaN:NaN:NaN

Speaker: Rachit

Type: CLS - Talk (Open Tech Summit)

Expertise:

Event: Devcon

Date: Nov 2026

AI can generate code in seconds, but contributing successfully to a real open-source project requires much more than producing a patch. In this practical session, we will walk through the journey from finding a GitHub issue to getting a pull request ready for review and merge. Using examples from the FOSSASIA eventyay project, we will look at how AI can help developers understand an unfamiliar codebase, trace relevant code paths, explore existing patterns, draft changes and create tests. The session will also cover the parts that still require engineering judgment: choosing the right issue, verifying the root cause, keeping changes within scope, following project architecture, testing real behavior and responding to maintainer feedback. The goal is to show that you do not need to understand an entire large codebase before contributing. With the right workflow, AI can significantly reduce the barrier to entry — while the contributor remains responsible for making the change correct, maintainable and useful to the project. Participants will leave with a concrete workflow they can use to start contributing to FOSSASIA and other open-source projects.

Categories

Community