FRESH

Hacker News

Home

Show HN: Zenflow – orchestrate coding agents without "you're right" loops

30 points by andrewsthoughts

by sfc32

1 subcomments

The multi-LLM approach is a great direction and I like the polished feel of the application. Moving up to a more project managenent approach is welcomed. I will download and give it a go.
One thought - vendors like cursor.ai have the benefit of highly tuned prompts, presumably by programming language, as the result of their user bases. How is it possible to compete with this?
On another note, I have played around with v0 etc, but AFAIK there is no really good UX/UI AI tool that can effectively replace a designer in the way that coding tools are replacing engineers (to a certain extent).

by leemalmac

1 subcomments

Spent a bit of time with the app. I use Zencoder plugins for my personal projects therefore already familiar with their ecosystem.
First of all kudos for the nice UI. I like when apps looks well. Onboarding process was smooth. I paired it with Zencoder's agent (as mentioned I use their VSCode plugin and already had a sub).
I used it to implement a small refactoring for my side project. What I like compared to plugins, I did not have to switch between agents or explicitly ask to write a plan/spec. It's I guess one of the core ideas behind the app and feels really AI-ish because it's not code editor (similar to claude code). The only thing I missed in the process is rendered markdown for previews. But I did not used the app for long, maybe there is an option to render markdown.
Overall great experience so far. Gonna explore it more. Wanna try it with Gemini and Claude Code. Again kudos it's not locked to use only Zencoder's agents.

by redhale

1 subcomments

This looks fantastic and I'm excited to try it today!
One question: I see this supports custom workflows, which I love and want to try out. Could this support a "Ralph Wiggum"-style [0][1] continuous loop workflow? This is a pattern I've been playing around with, and if I could implement it here with all the other features of this product, that would be pretty awesome.
[0] https://paddo.dev/blog/ralph-wiggum-autonomous-loops/ [1] https://github.com/onorbumbum/ralphio

by youkainoniichan

1 subcomments

Tested it for a while. Great that I can finally run my SDD workflows easily without juggling bunch of Claude Code commands in terminal.
Also, I found unexpected use case for it. Even when I need to only change couple lines of code, I just run quick fix workflow for it, because Zenflow automatically creates worktree, branch, commit etc. And PR is created with few clicks. It'll seems like a minor thing, but it irritates me a lot to do all this stuff myself for small changes. One thing I miss here is automatic PR name and description creation according to templates my company uses.

by redhale

1 subcomments

Is it possible to see the prompt files for the built-in workflows? I find them to be quite good, but not exactly what I want. My preference would be to simply tweak them slightly rather than starting from scratch with a custom workflow.

by xtiansimon

1 subcomments

> “…agents getting stuck in loops, apologizing, and wasting time. We tried to manage this … So we built Zenflow…Cross-Model Verification, Parallel Execution, Dynamic Workflows”
So you got me with the hook, and you bullet three features, but where’s the resolution of the hook issue? You left me with the hook?? What am I missing?

by edmundsauto

1 subcomments

It looks like the main difference in the plans is the premium LLM calls, but what does that add if I just bring my own key?
I am just a hobbyist but was curious how you’re thinking through the pricing plans.

by intuxikated

0 subcomment

no linux version :( also, how does this compare to something like vibe-kanban?

by thecoderpanda

1 subcomments

The multi-model approach makes sense. We've noticed different models handle different things better, so being able to run them side by side is pretty useful. The dynamic workflow stuff is neat. Most tools are too rigid once you start. Will be interesting to see how it handles unexpected turns.

by Pablosanzo

1 subcomments

This is the next step after SDD: a system that enforces the orchestration to execute the spec. I appreciate that you can bring your own agent (Claude Code, Codex, Gemini, Zencoder)

by cycahnh

1 subcomments

ok, this tool really did some magic for my poor promt "create a game like google chrome has when wifi is off". i also like that it kinda teaches me on proper spec development and thinking for me about the tests and things i needed to specify in the first place.
nice

by kelsolaar

1 subcomments

The app is really good, gave it a quick spin earlier, quite like it!

by Doublon

2 subcomments

FYI: advanced tracking protection in Firefox breaks your download form

by celeryd

1 subcomments

The language used on the website is very fresh! They are brave enough to call bad AI output "slop", which immediately makes me think they are trustworthy, that they are in the know. An AI bandwagoner wouldn't be brave enough to call it slop.
Then there's a blurb about the CEO who claims "AI doesn't need better prompts. It needs orchestration." which is something I have always felt to be true, especially after living through highly engineered prompts becoming suddenly useless when conditions change because of how brittle they are.
I might even give this a shot and I usually eschew AI plugins because of how cloud connected they are.
I am a nobody, but I think these people are making a bunch of right moves in this AI space.

by gk39

1 subcomments

Interesting! Just tested and it's quite impressive so far. I use multi-agent workflows on a daily basis. Overseeing them and limiting hallucinations has become a major pain for me. This is much needed.