Spec Coding by Capacity - Vibe Coding with a planning assistant to build with clarity
by•
Most AI app builders jump straight into building.
That feels fast until your app gets messy, inconsistent, and nothing like what you imagined.
Today, we’re introducing Spec Coding in Capacity.
Instead of building immediately, Capacity now lets you define your app first with the help of an AI co-founder that asks the right questions before any code is generated.
More structure upfront.
Far less refactoring later.
Much better results.
Replies
Really interesting approach with Spec Coding! As a full-stack dev building SaaS apps (DeadlineKeeper for college applications), I've been using BMAD Method (Breakthrough Method for Agile AI Driven Development) with Claude Code. The idea of defining structure upfront with an AI co-founder resonates with me - BMAD has 21 specialized AI agents that help architect before coding. Will definitely check out Capacity to see how your spec coding compares! 🚀
Capacity
@michael_antoine love it! BMAD is definitely one of our big inspirations 🔥
Nice! Does Capacity follow a structured planning phase or is it more direct code generation? With BMAD I map out architecture upfront before Claude touches anything - wondering how you guys approach that. Already adopted BMAD for DeadlineKeeper. Good luck with the launch! Launching DeadlineKeeper soon myself
Great! How is this different from vibe coding tools? Like Lovable
Capacity
@praasshant_dubey we strongly committed on spec coding. The issue with vibecoding tools is they incitate you to build first, but this approach is not scalable. You end up with an application that lies on a growing technical depth.
With spec coding, you start with planning the features you want to implement with our specialized AI agents, and then you implement. AI output becomes more deterministic and you make your application scalable.
Spec coding tools are baked in Capacity.
Auto-Hashtag API
$69/month for even one custom domain? Industry standard is $25, and Dyad.sh allows one even on their free plan.
Direct Github integration cxoming soon...?
Also, as for the problem with AI "not asking questions," this is why we RAG it: we tell our AI tools, "when something is unclear, always ask questions before you answer or build."
Vibe Mode / Spec Mode: I read your explanations, and now have absolutely no idea which to choose. You need a help page with example(s).
Finally, I did get in there, found the demo does not let me enter a prompt; doesn't work.
Oh, bnut the Mini Pack, for when we get stuck and need just a few more credits: brilliant!
Capacity
@osakasaul The correct way to look at the platform is as a whole. Spec coding is baked in Capacity to help develop complex features faster with serenity. Capacity offers spec coding + hosting/custom domain + code download. This is not something you see on other platforms, thus the different pricing. Ours may not fit your needs, I get it and respect that. This is personal choices.
Another point is we are not VC backed. We can't afford free plans. The demo has been designed to showcase the UX/UI of the project page so you can understand the main functionalities of the platform before committing to it. It is a compromise for what we can afford to show. And we find it fair.
I get your point about Vibe Mode / Spec Mode, but I disagree with "this is why we RAG it". Non technical people don't know what RAG is and a lot of them are afraid to use AI tools. You feeling confortable with conversing with AI and asking for challenge is not the case for everyone. That's why we developed specialised agents: to guide users and make them feel confortable with the process. Clarifying questions and challenges are baked in our specialised agents so users don't have to explicitly ask for it.
Btw, we have a dedicated support on Discord and WhatsApp, so if you faced any frustration using our platform (which seems to be the case), feel free to reach out there. We'll take time to help you.
My previous AI projects always turned into a mess after a few prompts. This "plan first" approach is a lifesaver for someone who isn't a pro developer.
Capacity
@daiphoon I strongly agree! Planning makes all the difference
Having used other vibe coding tools, excited to try another method to get started! Is this already connected on the backend to a DB, and does it support something google login, or payment systems?
Capacity
@gayathri_kamath backend relies on your Supabase account. To integrate google login, payment providers or any other 3rd party platform, you can co-write coding tasks with our specialized agents: they will deal with the technical strategy for you
The "planning first" approach addresses the biggest pain point in vibe coding – fast initial iterations that turn into technical debt. Most AI builders optimize for speed-to-first-render, not maintainability.
This spec-first flow reminds me of design systems thinking: define constraints upfront, iterate freely within them. Does the AI co-founder maintain spec consistency across revisions? That continuity would be critical for teams building beyond MVPs.
Capacity
@jacky0729 our planning system is broader since it's not only at the task level but at the project level as well (PRD, design specs...). Updating your PRD will produced adjusted coding tasks, and the coding agent will deal with adjusting the implementation of the platform.
In other words, the implementation of the platform is the mirror of your specs.
The spec-first approach resonates—I've seen plenty of vibe-coded apps where early assumptions snowball into major rewrites. I'm curious how the system handles evolving requirements mid-project. Does the AI co-founder flag when new requests conflict with the original spec, or does it silently adjust?
Capacity
@yamamoto7 our planning system is broader since it's not only at the task level but at the project level as well (PRD, design specs...). Updating your PRD will produced adjusted coding tasks, and the coding agent will deal with adjusting the implementation of the platform. In other words, the implementation of the platform is the mirror of your specs
The co-founder is your assistant that has the knowledge of all the specs of your project. It may tell you if the feature you want to implement is considered out of the MVP scope, but won't prevent you from doing so
I like the co-founder concept—does it ask clarifying questions at each step, or does it front-load all the planning before generating anything?
Capacity
@jacky0729 your project specifications are generated step-by-step. During each step, you are guided by a specialized AI agent that ask you clarifying questions. Once your project specifications are written, you can move on to coding tasks. Coding tasks are the bridge between your project specs and the implementation of your app. So it goes project specs -> Coding tasks -> Implementation
Would love to learn how Capacity is different from Lovable and Base44!
Capacity
@joyce_qiao1 we strongly committed on spec coding. The issue with vibecoding tools is they encourage to build first instead of planning, but this approach is not scalable. You end up with an application that lies on a growing technical debt.
With spec coding, you start with planning the features you want to implement with our specialized AI agents, and then you implement. AI output becomes more deterministic and you make your application scalable.
Spec coding tools are baked in Capacity.
Looks good, good luck.
What is supported for backend and frontend?
Capacity
@dexiv thanks for the support 🙏 We made opinionated choices: vitejs + react for the frontend and supabase for the backend. We would love to support Next.js as well, but this is off-limits at the moment.