OpenAI

What Will You Build With Coding Agents That Don’t Quit? | DevDay 2026

Published 2026-11-11 · Duration 27:09

Summary

The presentation details how advanced AI agents (Codex, Astra, GPT-6) can automate complex, long-running engineering tasks, extending agent capabilities from simple code generation to sustained, multi-week maintenance of Continuous Integration (CI) systems. Key advancements include the ability to manage context over long horizons, parallelize work using child threads, and integrate with external tools (GitHub, Slack) to autonomously debug flaky tests, manage pull requests, and coordinate fixes, significantly reducing manual engineering overhead.

Download summary

Key takeaways

  1. Sustained Automation for CI/CD 17:10

    An agent can autonomously maintain CI health over extended periods (e.g., six weeks), running millions of tests, opening over 100 PRs per week, and merging over 200 fixes, even handling complex issues like Heisen bugs and non-deterministic floating-point errors. (See 10:30)

  2. Advanced Agent Control Flow 22:00

    New features allow engineers to manage agent behavior by using child threads for parallel tasks, the `/goal` command for relentless task pursuit, and the `/side` command for querying without disrupting the main workflow. (See 13:20)

  3. Context Management and Scale 18:50

    The introduction of 'Compaction' allows models to maintain context over extremely long-horizon tasks (months) without degradation. Remote environments and Codex Cloud enable continuous work across different machines and surfaces. (See 11:30)

More digests on AI Agents

Technical details

  • Agent Architecture & Workflow 820s

    Agents can be given a high-level goal and trade-offs, allowing them to figure out the steps autonomously, rather than requiring prescriptive, step-by-step plans. (See 8:20)

  • Parallel Processing 1450s

    Using child threads and worktrees allows agents to work on multiple, non-sequential features (e.g., a 3D model and a website) simultaneously without causing merge conflicts. (See 14:50)

  • Debugging Hard Problems 1540s

    Ultra Mode provides deep reasoning time, allowing the agent to spin up sub-agents to investigate complex, single-point failures (like the GPU floating-point bug) that require sustained, focused effort. (See 15:40)

  • Integration and Monitoring 1400s

    Plugins (e.g., GitHub, Linear) connect the agent to external tools, allowing it to search issues, discuss PRs, and coordinate fixes. Heartbeat and scheduled tasks automate follow-ups and periodic summaries. (See 14:00)

Mentioned resources

  • Codex (AI Model/Agent)
  • Astra (AI Model)
  • GPT-6 Sol (AI Model)
  • Codex Cloud (Platform)
  • Agents.md (Configuration File)

Channel & topics

Watch on YouTube · Back to latest

This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.