> Markdown version of [/videos/1903-github-next-and-the-future-of-coding-idan-gazit](https://www.wearedevelopers.com/videos/1903-github-next-and-the-future-of-coding-idan-gazit). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# GitHub Next and the Future of Coding - Idan Gazit

Idan Gazit reveals why AI makes typing code obsolete. To survive, engineering teams must shift from writing syntax to curating agent-generated code and mastering architectural judgment.

- **Speakers:** Idan Gazit
- **Event:** Coffee With Developers
- **Published:** June 10, 2026
- **Duration:** 35:11
- **URL:** https://www.wearedevelopers.com/videos/1903-github-next-and-the-future-of-coding-idan-gazit

## Summary

GitHub Next lead Idan Gazit explores the shifting landscape of software engineering as artificial intelligence pushes the industry from raw code generation to code curation. With AI models effectively reducing the conceptual cost of writing code to zero, the physical act of typing now represents just a fraction of developer time. This rapid evolution is straining traditional workflows, as massive, agent-generated pull requests overwhelm continuous integration infrastructures like GitHub Actions. To adapt, the industry must fundamentally rethink developer communication, abandoning waterfall-style, post-draft pull requests in favor of real-time, multi-player coordination layers reminiscent of Figma or Google Docs where human intent and technical constraints are aligned earlier in the process.

As large language models operate like untrained junior developers, the core competency of human engineers is transitioning toward systemic architectural judgment and context management. While autonomous agents can seamlessly read codebases to understand authorization flows or generic algorithms, they completely lack the specific business and organizational context necessary for successful enterprise deployments. Maintaining a reliable pipeline of high-quality talent in this new paradigm requires organizations to utilize AI as an "infinitely patient tutor" for junior engineers. Rather than letting entry-level talent atrophy, teams must encourage juniors to build a deep, hands-on "fingertip feel" for steering AI so they can eventually assume senior leadership roles.

Ultimately, attempting to measure this new era of developer productivity through superficial metrics like "token maxing" is fundamentally flawed, much like historical attempts to evaluate performance primarily by counting lines of code. True software engineering value is anchored in architectural judgment, continuous repository-level refactoring, and complex context translation rather than file-level syntax generation. Navigating this future requires developers to aggressively map new AI tooling to their existing workflows, deliberately prioritizing cognitive orientation and system design over brute-force typing.

**Keywords:** agentic coding environments, real-time code collaboration, ai-assisted software engineering, continuous integration infrastructure, pull request workflows, developer cognitive load, junior developer onboarding, software developer productivity metrics, repository-level refactoring, llm context management, github actions scalability, coding ui/ux interfaces, ai token consumption, software architectural judgment, prompt engineering techniques

## Chapters

1. **Mission and goals of the GitHub Next research team** (00:18) — Exploring second-order impacts of artificial intelligence to make software development faster and more accessible.
1. **Adapting collaboration to zero-cost code creation** (01:33) — When generative AI handles typing, developer alignment must happen before agents draft multiple code variations.
1. **Incorporating human context into agentic software workflows** (03:09) — Providing business context and human preferences helps guide AI agents toward successful organizational outcomes.
1. **Shifting from asynchronous pull requests to real-time collaboration** (04:33) — Real-time communication layers help integrate human intent with agent actions earlier in the development process.
1. **Infrastructure scaling challenges from oversized agent pull requests** (07:40) — Agentic environments generate massive pull requests that overwhelm continuous integration and code hosting infrastructure.
1. **Elevating junior engineers into technical leadership roles** (10:39) — Organizations must invest in junior developers to build the senior engineering talent required to supervise AI models.
1. **Evolving user interface metaphors from files to systems** (16:32) — AI coding tools are moving away from file-level text selection toward system-level refactoring instructions.
1. **Measuring developer productivity with artificial intelligence adoption** (19:03) — Justifying AI expenditure requires observing overall deployment speed rather than relying on flawed granular metrics.
1. **Prioritizing cognitive orientation over raw code generation** (22:50) — Generative AI provides the highest value by helping engineers understand existing systems rather than simply typing code.
1. **The hardware accessibility gap for local AI processing** (24:46) — Running capable local language models requires expensive hardware, forcing developers to rely on cloud subscription services.
1. **Evaluating distributed computation networks for AI model execution** (31:15) — Leveraging peer-to-peer networks for model computation remains impractical due to severe container security vulnerabilities.
1. **Developing AI tooling intuition through continuous practice** (32:33) — Engineers must actively practice prompting and context engineering to build a fingertip feel for AI capabilities.

## Related Moments

- [Introduction to GitHub Next and AI prototyping](https://www.wearedevelopers.com/videos/1268-innovating-developer-tools-with-ai-insights-from-github-next) (from "Innovating Developer Tools with AI: Insights from GitHub Next")
- [Shifting developer workloads and realistic AI productivity gains](https://www.wearedevelopers.com/videos/1830-wearedevelopers-live-speculaitions) (from "WeAreDevelopers LIVE - SpeculAItions")
- [Motivations for adopting AI to enhance developer productivity](https://www.wearedevelopers.com/videos/1266-navigating-the-ai-revolution-in-software-development) (from "Navigating the AI Revolution in Software Development")
- [Impact of AI tools on developer collaboration](https://www.wearedevelopers.com/videos/1924-ai-s-threat-to-uniqueness-and-belonging) (from "AI's threat to uniqueness and belonging")
- [Focusing on developer happiness at GitHub Next](https://www.wearedevelopers.com/videos/100069-building-the-next-generation-of-ai-developer-tools) (from "Building the next generation of AI developer tools")
- [Understanding GitHub Copilot and core developer benefits](https://www.wearedevelopers.com/videos/1011-github-copilot-beyond-the-basics-10-ways-to-elevate-your-coding) (from "GitHub Copilot Beyond the Basics - 10 Ways to Elevate Your Coding")

## Related Articles

- [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care)
- [Transforming Software Development: The Role of AI and Developer Tools](https://www.wearedevelopers.com/magazine/527-transforming-software-development-the-role-of-ai-and-developer-tools)
- [What is Software Engineering in the Age of AI?](https://www.wearedevelopers.com/magazine/640-what-is-software-engineering-in-the-age-of-ai)
- [How we Build The Software of Tomorrow](https://www.wearedevelopers.com/magazine/120-how-we-build-the-software-of-tomorrow)

## Related Jobs

- [Principal Product Manager, Agent Platform](https://www.wearedevelopers.com/jobs/ext/277541-principal-product-manager-agent-platform) at **GitHub**
- [Senior Software Engineer](https://www.wearedevelopers.com/jobs/ext/15942-senior-software-engineer) at **GitHub**
- [Staff Developer Advocate, GitHub Security Lab](https://www.wearedevelopers.com/jobs/ext/1921051-staff-developer-advocate-github-security-lab) at **GitHub**
- [Staff Software Engineer, Copilot Experiences](https://www.wearedevelopers.com/jobs/ext/164361-staff-software-engineer-copilot-experiences) at **GitHub**
- [Principal Software Engineer, Enterprise AI Platform](https://www.wearedevelopers.com/jobs/ext/1467292-principal-software-engineer-enterprise-ai-platform) at **GitHub**
- [AI Software Engineer (Germany)](https://www.wearedevelopers.com/jobs/48317-ai-software-engineer-germany) at **Sunhat**