One of my strongest AI-assisted development wins - https://www.autoplay.ai/ : a SaaS roadmap orig...One of my strongest AI-assisted development wins - https://www.autoplay.ai/ : a SaaS roadmap orig...
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
One of my strongest AI-assisted development wins - https://www.autoplay.ai/ : a SaaS roadmap originally planned across nearly 2 years, shipped in around 1 month.
I worked on a multi-tenant AI platform with voice agents, dashboards, integrations, background workflows, user management, and production infrastructure.
Claude and specialized AI agents were part of the development process from day one. The real advantage came from how I used them, not simply how often.
I kept tasks tightly scoped, gave agents clear responsibilities, reused the right project context, and brought Claude in where deeper reasoning was actually needed.
That helped me keep Claude token usage surprisingly low while still getting the quality I needed across architecture, development, debugging, testing, and reviews.
The result was a much longer development roadmap compressed into weeks, while still keeping the system clean enough to maintain and extend.
For me, that is the real value of AI-assisted development: more engineering output, less wasted context, and fewer tokens.
A: AI-first. No tabs, no dashboards. The app is one conversation with a coach that already knows you slept six hours and squatted heavy on Tuesday. You log sets by talking. The plan rewrites itself mid-workout.
B: The modern standard. Home, today's workout, set-by-set logging, class booking, progress. Everything a member expects, done properly.
Same brand, same components, same build quality. The only real difference is how much you're asking the user to unlearn.
Going with A here, the idea of the plan rewriting itself mid-workout instead of you scrolling a dashboard feels like where fitness apps eventually land. Would you actually ship the AI-first version to real users right now, or is it more of a thought experiment at this stage?
Created an AI-powered lead generation and outreach tool for finding and converting local business leads.
The system scrapes Google Maps, analyzes business websites with Gemini AI, and generates personalized pitch emails automatically.
I built the complete pipeline from scraping to AI analysis and outreach.
Last night I demoed my job-feed agent live at AI Tinkerers Barcelona. I think it went well!
It scores each Contra posting out of 10 against rules I wrote in plain text, drafts the good ones, and declines the rest by citing the rule.
Recording, map and build order: https://redmage.cc/ait-bcn