---
title: "Discussion on \"AI Workflow Update\" | Hashnode"
description: "Discussion on \"AI Workflow Update\". In my previous post, I described how I used Labor0 and Codex to run dozens of tasks in parallel. My workflow has changed since then. I no longer use Labor0, and I now work with skills that I have made"
url: "https://hashnode.com/posts/2026-10-8-ai-workflow-update/6ac6f8bdb2e680c409ab12c8"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [AI Workflow Update](https://kdy1.dev/2026-10-8-ai-workflow-update?utm_source=hashnode&utm_medium=feed)

In my previous post, I described how I used Labor0 and Codex to run dozens of tasks in parallel. My workflow has changed since then. I no longer use Labor0, and I now work with skills that I have made

Oct 8 · 4 min read · kdy1.dev  
Read the article

## Written by

[DongYun Kang](https://hashnode.com/@kdy1)

@kdy1 · South Korea

  
[View profile](https://hashnode.com/@kdy1)

Creator of SWC

CEO of Delino. I created SWC, an open-source compiler project, and previously worked at Deno and Vercel.

## Responses 3

Markdown supported · ⌘↵ to post

[netproxy](https://hashnode.com/@argumentmoney8117)

[Oct 8](https://hashnode.com/posts/2026-10-8-ai-workflow-update/6ac6f8bdb2e680c409ab12c8/comment/6ac81c52feab7f2c88ace446)

The issue tracker as a prompt repository is a framing I want to borrow. One question though: the stacked PR batch still needed several rounds of review feedback and CI fixes, so is the real win in parallelizing the mechanical work while the judgment-heavy review part stays serial? The CPU and memory cost of dozens of subagents also sounds worth tracking over time. Thanks for writing it up in detail.

[Airan](https://hashnode.com/@airan)

[Oct 8](https://hashnode.com/posts/2026-10-8-ai-workflow-update/6ac6f8bdb2e680c409ab12c8/comment/6ac79bfd826dc77303693f33)

This was actually really interesting to read. I think the coolest part isn’t even the tools themselves, but how you keep changing your workflow when you find a better way of working. A lot of people just stick with whatever setup they started with, so seeing you experiment and rebuild the process is pretty refreshing. Really enjoyed this one!

[Blaze](https://hashnode.com/@moon321)

[Oct 8](https://hashnode.com/posts/2026-10-8-ai-workflow-update/6ac6f8bdb2e680c409ab12c8/comment/6ac7388a01c233bdd8b51ae0)

Using the issue tracker as a prompt repository is a smart idea. The stacked PR workflow also seems much easier to manage at scale.
