Hey Contra π Two months ago I posted Promptly here as a work-in-progress and said I'd launch in ...Hey Contra π Two months ago I posted Promptly here as a work-in-progress and said I'd launch in ...
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
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 β 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:
β 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.
β Nothing ever gets lost. It snapshots before anything risky, so you can roll back a single module or the whole project.
β 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 β or what missing one burned you?
Every comment on the last post shaped what got built. Thank you for that π
Congrats on shipping "AI proposes, code decides" is the right split, and routing all 16 agents through typed tool calls (instead of raw DB access) is what actually makes that enforceable rather than aspiration.
Congrats on shipping! Love the emphasis on hard guardrails and deterministic validation. Thatβs exactly how you build trust with LLMs. Excited to poke around the build.
Huge congrats, Kai! Top 1% with 230 pts is massive super inspiring for freelance designers like us just starting out. Whatβs the one thing that helped you boost your discovery score the most?
Exploring 3D interactions and brutalist scale for Kinetix β a portfolio concept centered on design systems and digital products.
Focused on balancing heavy typography with fluid, tactile motion so the 3D element feels integrated rather than decorative.
Curious to hear your thoughts: does the 3D rotating showcase feel smooth and intuitive, or do you prefer flat, high-speed interactions for portfolio heroes?
The rotating 3D works here precisely because you kept it integrated, not decorative, so it reads as intent rather than showing off. For a portfolio hero I usually lean flat and fast, but this earns the motion. That heavy Kinetix wordmark has real physical weight.