Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Async – Claude code and Linear and GitHub PRs in one opinionated tool

github.com

Post reply on HN
Print view View original

41–49 of 49 posts

Re: Show HN: Async – Claude code and Linear and GitHub PRs in one opinionated tool

#41

Post by dbbk »

chis wrote: post #14

Great pitch, you've articulated the pain point super well and I agree with it. I have personally had no luck with prompting models to ask me clarifying questions. They just never seem to think of the key questions, just asking random shit to "show" that they planned ahead. And they also never manage to pause halfway through when it gets tough and ask for further planning. My question is how well you feel it actually…

Interesting you say that. My workflow is just to use Claude Code with Opus in Plan mode, have it write a plan, and ask "What clarifying questions do you have for me" and it always prompts me to answer very good questions.

Re: Show HN: Async – Claude code and Linear and GitHub PRs in one opinionated tool

#43

Post by wjsekfghks »

basic_banana wrote: post #42

It is pretty similar to async code, but i guess async is more like linear, while async code is more likely a codex cloud for claude code. https://github.com/ObservedObserver/async-code

cool, let me check it out

Re: Show HN: Async – Claude code and Linear and GitHub PRs in one opinionated tool

#44

Post by 7thpixel »

If you'd like some feedback, I ran this through my algo and analyzed what is unclear and potentially risky for bring this forward:

What's unclear:

Exact AI coding capabilities, free tier limitations, and the revenue model beyond the hosted version.

Risky Assumptions:

- Users will find the UX/UI sufficiently intuitive for immediate adoption.

- Companies will see ROI in reduced dev time/cost when using Async.

- The AI agent can clarify requirements accurately on a variety of tasks.

Hope this helps!

Re: Show HN: Async – Claude code and Linear and GitHub PRs in one opinionated tool

#45

Post by wjsekfghks »

7thpixel wrote: post #44

If you'd like some feedback, I ran this through my algo and analyzed what is unclear and potentially risky for bring this forward: What's unclear: Exact AI coding capabilities, free tier limitations, and the revenue model beyond the hosted version. Risky Assumptions: - Users will find the UX/UI sufficiently intuitive for immediate adoption. - Companies will see ROI in reduced dev time/cost when using Async. - The AI…

Thank you so much for the feedback! Could you elaborate more on the point about UX/UI. We are trying to see what we can do to make onboarding and issuing the first task as easy as possible. I'd love to hear your insights on that

Re: Show HN: Async – Claude code and Linear and GitHub PRs in one opinionated tool

#46

Post by selinkocalar »

The hard part with tools like this is maintaining context across different data models. GitHub PRs, Linear tickets, and LLM conversations all have different information architectures. Are you doing any semantic linking between related items, or just surface-level aggregation?

Re: Show HN: Async – Claude code and Linear and GitHub PRs in one opinionated tool

#47

Post by wjsekfghks »

selinkocalar wrote: post #46

The hard part with tools like this is maintaining context across different data models. GitHub PRs, Linear tickets, and LLM conversations all have different information architectures. Are you doing any semantic linking between related items, or just surface-level aggregation?

We use one model across all three surfaces called Task. Those do have different information architectures, i.e. Linear tickets have correspondence or comments, LLM conversations have chat history and code reviews have diffs and comments. But, at the end of the day, all those information are used to output the correct code and we are doing just that.

Re: Show HN: Async – Claude code and Linear and GitHub PRs in one opinionated tool

#48

Post by wjsekfghks »

reilly3000 wrote: post #37

Thumbs up for dark mode. I really want to love this but I can’t get over the idea of paying GCP to have cloud run clone my repo over and over again every time I interact with Async. I’m still going to try it, but I think I’d rather rent a VM and just have it be faster. This is coming from someone who deals with big fat monorepos, so maybe it’s not that bad for the average user.

we are trying to run execution locally using local claude code
Post reply on HN