If you do sprint planning, you can figure out which tasks have a short enough time horizon that the AI are competent enough to actually do the task correctly, and break down the tasks which they can't do reliably. If this sentence is confusing, see my answer to you in the other thread.
Sprints also gives you insight into when development velocity (per token rather than per time, though for both humans and AI this works out as money) slows down from technical debt.
Or at least it can in principle; I think the speed of AI is likely to make management less of an art and more of a science, with things like "technical debt" and "task estimation" going from gut feeling to something quantifiable, and this may in turn end up replacing Agile (and all the others) with something new.
Vibe coded product, vibe coded marketing website, AI-generated marketing copy, a testimonial from an AI-generated mascot and seemingly fake identities for the founders. Of course this garners some points on modern day HN.
> SprintiQ started as an AI planning tool for agile teams. Now we run our entire engineering org on AI agents managed by Turbo. Two founders. Zero human devs. Shipping product.
No video. We hustled to get this out OSS and forgot about the demo; check out sprintiq.ai for the cloud version if you want to click around immediately; sunset on b2c soon. Self-hosted takes about 10-15 minutes with a Supabase project and an Anthropic API key. Happy to answer any questions here.
I don’t understand why coding agents are playing dress-up with these human engineering rituals.
Why would coding agents do Sprint planning? Isn’t the claim “code is basically free now”? Why would I budget for something that’s free?
I think your confusion is based on the same mistake you make here about what a "time horizon" is: https://news.ycombinator.com/item?id=48018160
If you do sprint planning, you can figure out which tasks have a short enough time horizon that the AI are competent enough to actually do the task correctly, and break down the tasks which they can't do reliably. If this sentence is confusing, see my answer to you in the other thread.
Sprints also gives you insight into when development velocity (per token rather than per time, though for both humans and AI this works out as money) slows down from technical debt.
Or at least it can in principle; I think the speed of AI is likely to make management less of an art and more of a science, with things like "technical debt" and "task estimation" going from gut feeling to something quantifiable, and this may in turn end up replacing Agile (and all the others) with something new.
Vibe coded product, vibe coded marketing website, AI-generated marketing copy, a testimonial from an AI-generated mascot and seemingly fake identities for the founders. Of course this garners some points on modern day HN.
> SprintiQ started as an AI planning tool for agile teams. Now we run our entire engineering org on AI agents managed by Turbo. Two founders. Zero human devs. Shipping product.
Good luck.
No video. We hustled to get this out OSS and forgot about the demo; check out sprintiq.ai for the cloud version if you want to click around immediately; sunset on b2c soon. Self-hosted takes about 10-15 minutes with a Supabase project and an Anthropic API key. Happy to answer any questions here.
The site looks 100% vibe slop.
Got a demo site or video?