←
Hoang Nguyen2,555 posts
Hoang Nguyen avatar

Hoang Nguyen

@codeaholicguy

engineering @ ShopBack; creator of ai-devkit.com

◷ Joined August 2013▧ 231 Photos and videos
Hoang Nguyen avatar
Hoang Nguyen@codeaholicguy·6h

2026 was the year of agent orchestration ai-devkit.com thanks me later

2022 was the year of autocomplete 2023 was the year of chat 2024 was the year of the AI IDE 2025 was the year of coding agents 2026 was the year of agent orchestration 2027 will be the year of outcome engineering

Hoang Nguyen avatar
Hoang Nguyen@codeaholicguy·13h

anthropic's claude code team says claude now writes and reviews about 90% of their code, and the boring lesson is to make the agent prove it worked. without a check you're stuck babysitting 1 or 2 sessions. the other half is who runs the check. in my setup one lead agent gives workers (codex, opencode, pi, grok cli, muse code, antigravity cli) a scoped task, waits on each one and reviews the result before it starts the next thing. I cap it at 3-4 workers so I'm not reading every diff myself. it's open source if you want the same setup: github.com/codeaholicguy/ai-…

Hoang Nguyen avatar
Hoang Nguyen@codeaholicguy·Nov 10

Classic “big upfront planning” still fits poorly inside daily/weekly/bi-weekly iteration for most product work. When that uncertainty is high, locking in a large plan and then executing for weeks creates lag between assumption and evidence. AI makes the execution cheap, but the cost of a wrong assumption still grows with how far you travel before checking. Where AI does change the calculus is that you can now afford more precise thinking inside short cycles rather than instead of them. Because an agent can turn a reasonably detailed spec into working code in minutes or hours, the lag between writing a plan and seeing its consequences collapses. What used to take months of waterfall lag can now be an afternoon of revise-and-rebuild. That is not traditional waterfall; the plan is never frozen and the feedback is continuous. Fast feedback, responding to change, customer collaboration, and working software over comprehensive documentation become more important. Fixed two-week sprints and story-point estimation may matter less; the ability to change direction based on evidence and to keep shipping increments that produce learning still matters a great deal. So big upfront planning can be useful for certain classes of decisions and can be done more rigorously than before. It fits continuous iteration when it is scoped, revisable, and subordinated to the learning cycle rather than allowed to freeze the path from idea to validated production. The practical question is how large a plan can we write, execute with AI, and validate before the assumptions are likely to be wrong? That size is usually smaller than classic waterfall and larger than pure just start coding.

Hear me out: We hated "waterfall" because after Big Upfront Planning, implementation took FOREVER, and by the time we were done, the plan was out of date But with AI, implementation is rapid (100x faster, or more, than before) So Big Upfront Planning can now make sense?

Hoang Nguyen avatar
Hoang Nguyen@codeaholicguy·Nov 9

codeaholicguy.com/2026/11/06…

it's shocking that software engineering has transitioned to 100% AI written in such a short time. it's more shocking that somehow we, the SWEs, are all just continuing on as if nothing happened. It writes C++ better than I ever could, but the problem of making sure it works didn't magically disappear. we are just shipping enormously more volume at higher quality.

Hoang Nguyen avatar
Hoang Nguyen@codeaholicguy·Nov 8

Glad that this idea of having multiple layers of agents orchestrating other getting more and more adoption x.com/codeaholicguy/status/2… If you are finding a seamless solution for building your setup, give ai-devkit a try

I've changed how I work over the last few weeks. I now have one lead agent for each area of focus, running all the time, and a chief of staff agent that oversees them. Each lead manages its own sub-agents that write code, test it, chase reviews, and coordinate with team members. Everything I need to decide or review comes into one prioritized queue, a simple local web app. Each product review includes screenshots and a video demo of the feature. I clear the queue in batches, mostly by voice and keyboard shortcuts. The leads also bring back ideas I hadn't considered. Working from one queue, instead of switching between dozens of chats, has cut a lot of mental overhead. The system keeps learning my preferences and distilling my judgment into a "Brian brain," so its recommendations and first drafts get better before they reach me. The goal is fewer corrections per change. Every change still goes through the same human review and security checks. It is eliminating tasks, not human judgment. What an exciting time to push the frontier of productivity, especially as we build the economy for agents (agentic finance). We should all keep pushing in this direction.

Hoang Nguyen avatar
Hoang Nguyen@codeaholicguy·Nov 8

Normal PC user: - 8GB RAM: Enough - 16GB RAM: Perfect - 32GB RAM: Overkill Multi-agents orchestration user:

Normal PC user: - 8GB RAM: Enough - 16GB RAM: Perfect - 32GB RAM: Overkill Chrome user:

Hoang Nguyen avatar
Hoang Nguyen@codeaholicguy·Nov 8

put care to every detail then you can build great product

my eyes are bleeding though. I think this would be a good designer test. "find all the ui problems in this one image". - vertical and horizontal alignment is missing - buttons are rounded and square. also various sizes - spacing - ... send this to your agent to fix :)

Post attachment
Marc Randolph avatar
⟳ Hoang Nguyen retweeted
Marc Randolph@marcrandolph·Nov 3

Not sure who needs to hear this, but being everywhere isn't leadership. It actually makes you the bottleneck.

Uncle Bob Martin avatar
⟳ Hoang Nguyen retweeted
Uncle Bob Martin@unclebobmartin·Oct 31

TL;Dr:

Post attachment
DHH@dhhOct 30

If this is what has employees at Proton in revolt, they're in for a rough ride as the age of agents unfold. There is nothing scandalous in this memo. It's hilarious that 404 is treating it as such.