The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
StudioOS – Building an AI-First Operating System for Indie Studios
https://app.flowstep.ai/file?activeFileId=ed2e51f7-581a-460a-a020-92da04ca5590
StudioOS is an AI-powered operating system for game studios and solo founders. Instead of juggling documents, tasks, roadmaps, and AI tools, everything lives in one workspace powered by intelligent agents.
For this prototype, I used Flowstep AI to rapidly design the user experience while keeping the product documentation and implementation synchronized through MCP.
What I Built:
- AI-first dashboard
- Multi-agent workspace
- Project & roadmap management
- Team collaboration flows
- Settings and onboarding experience
My Process:
Rather than prompting Flowstep screen by screen, I connected it to my project through MCP using OpenCode.
Flowstep read my centralized project documentation (AGENTS.md and supporting docs), while OpenCode handled implementation and project context. This let me iterate much faster because both tools shared the same source of truth.
My workflow looked like this:
- Define product requirements in documentation.
- Use OpenCode + MCP to maintain project context.
- Ask Flowstep to generate and iterate on UI flows.
- Refine screens based on usability and product goals.
- Export the design back into the development workflow.
One interesting part is that OpenCode isn't listed in the current Flowstep MCP documentation, but it works well as a coding companion for this workflow.
Building StudioOS with Flowstep felt less like drawing screens and more like collaborating with a design teammate. The combination of Flowstep for UX and OpenCode through MCP for project context made rapid iteration surprisingly smooth.
Really like how you connected Flowstep and OpenCode around the same project docs. That shared context seems like it would make the whole design-to-build process much smoother. StudioOS also feels like a great fit for this kind of workflow. Good luck
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
Claude
Claude has entered the design space. How are you using it?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
Brand Design
The best brand designers are on Contra. Scroll to see what's trending in brand design. What are you building?
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?
Related posts
HEADROOM is the freelancer's fuel gauge: log one energy reading a day out of 100, see today's load against it, and export a capacity card to clients. I built it because I have tracked exactly this number in a notes file for a year and always wished it were an instrument instead. Built in Flowstep via MCP from Claude Code, with a locked brutalist design system and tons of love. 😍 🎉
I took part in the #FlowstepChallenge by designing and building EarnSignal — a product prototype that helps people discover realistic income opportunities, compare the evidence and risks behind them, and create a simple 7-day plan to test an idea before committing more time or money.
Designed in Flowstep and expanded into a responsive, interactive Next.js experience with personalisation, comparison tools, test plans, notes, reflections, and progress tracking.
Flowstep prototype:
https://app.flowstep.ai/file?activeFileId=4d41edc4-abe1-4e2d-b675-d3a62a83013f
Live project:
https://earnsignal-nine.vercel.app
DecisionOS — The Operating System for Organizational Intelligence
DecisionOS is a modern enterprise platform designed to help teams capture, analyse, approve, and remember every important business decision.
Instead of losing context across meetings, messages, and documents, teams can bring everything into one structured workspace—discussions, evidence, alternatives, risks, votes, approvals, and outcomes.
The working principle is simple: teams create a decision, add context and supporting evidence, compare possible options, identify risks, gather feedback, and complete a formal approval process. After the decision is made, DecisionOS tracks the result, records lessons learned, and preserves the full history for future teams.
The product was designed in Flowstep AI as a complete decision lifecycle experience, with AI-powered summaries, risk analysis, decision health, dependency mapping, voting, timelines, outcome reviews, and searchable organizational memory.
Think of it as GitHub for business decisions.
don't forget to include your flowstep link!