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
โข 21h
Still spinning up local databases for portfolio projects??
Here's the dev setup nobody talks about enough:
๐ฆ๐๐ฝ๐ฎ๐ฏ๐ฎ๐๐ฒ + ๐๐น๐ฎ๐๐ฑ๐ฒ ๐๐ผ๐ฑ๐ฒ via MCP
Here's the workflow:
โฆ Create your Postgres database instantly on Supabase
โฆ Connect it to Claude Code via the Supabase MCP server
โฆ Claude can read schema, write migrations, query data, and debug, all inside your project
What this actually means:
โฆ You describe what you need, Claude writes the SQL
โฆ Schema changes happen through natural language
โฆ Your database lives in the cloud from day one
โฆ Zero context switching between your editor and a DB client
The best part? Claude isn't just autocompleting code. It's operating your actual database โ understanding your tables, your relationships, your data.
This is what AI-assisted development looks like when the tools are actually connected.
If you're still managing a local db for every project, try this once. You won't go back.
#ClaudeCode #Supabase #AIEngineering #DeveloperTools #MCP #PostgreSQL
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
Related posts
They said "You have to start somewhere"
Started building "StyleFlow"
The app will be live on App Store & Google Play soon.
We Need to focus on helping a local business then we do multi salon.
Interviewed real people in person to gather feedback and improve the app.
The app is live, and the salon is actively using it. They love how smooth it is and how much it has helped automate tasks for both customers and salon owners.
๐ฏ Just DM me to get the access code and explore the Manage Your Salon feature, since the salon is currently using the app.
Live: https://styleflow-hub.base44.app/
Thank you for those who are supporting the app.
WE INTERVIEW AND INTRODUCE OUR PRODUCT TO REAL LOCAL BARBERSHOP BUSINESS.
Yes! you read it right. We are confident with the product and show it to public....
Terra โ AI Environmental Risk Platform
Designed the landing page and product UI for Terra โ a platform that helps land developers and engineering teams see environmental risk (soil stability, tree canopy loss, water table depth) before breaking ground.
The challenge:
Development decisions are usually based on estimates, not real ground data โ and by the time issues show up, itโs often too late to reverse them. The interface needed to make complex sensor/AI data feel immediate and trustworthy, without losing emotional weight.
The solution:
Raw, organic photography (wildflowers, grass, natural terrain) paired with clean glass-panel data cards โ creating a visual tension between โnatureโ and โprecision engineering.โ Bold editorial typography carries the emotional message, while translucent metric cards surface real numbers: soil stability, canopy loss %, water table depth.
A strong example of turning dense environmental data into something a non-technical stakeholder can understand in seconds.
Nice one
Hey Contra ๐
Two months ago I posted Promptly here as a work-in-progress and said I'd launch in about three weeks.
Then a health issue knocked me flat, and the three-week plan was gone.
I'm good now โ and as of today, the build is done. I just published the full case study as well.
Quick recap: after shipping 20+ projects as a tech lead, I kept watching the same thing break. A founder says one thing, the developer hears another, and a month in, the whole build is based on a misunderstanding nobody caught early.
Promptly closes that gap. You describe your idea in plain English; the AI interviews you, pushes back on the vague parts, and writes a developer-ready spec while you chat.
But the chat is the easy part. The real engineering is everything that stops the AI from being trusted too much:
โ It never touches the database. 16 agents can only propose changes through typed tool calls; backend code checks each one, and invalid calls get rejected and logged.
โ Nothing ever gets lost. It snapshots before anything risky, so you can roll back a single module or the whole project.
โ Spend is capped, always. Every AI call passes four checks before it fires, and each one is logged with its exact cost.
One line sums up the architecture:
The AI proposes. The code decides.
The model gets to be creative. It never gets to be in charge.
Full case study is on my profile, and the product is live if you want to poke at it.
One question:
Shipped anything with LLMs in production? What guardrail saved you โ or what missing one burned you?
Every comment on the last post shaped what got built. Thank you for that ๐
building solo, in public
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
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. Whatโs yours right now?