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
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.
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
Did a motion for the Cockpit concept ⁕ 🔈 ON
Design & Creative Direction: Me
Motion & Sound: Claude Code
Cockpit is an AI agent management platform concept that helps teams:
- Set boundaries
- Monitor activity
- Manage approvals
- Track knowledge sources
- Measure performance and costs
It brings together five key AI UX challenges:
👉 Autonomy
👉 Observability
👉 Human Approvals
👉 Context
👉 Analytics
The idea is simple:
As AI agents become more capable, the experiences we design around them need to make their actions more transparent, predictable, and manageable.
Thanks!
Human approvals is the part most agent UIs skip. Good call making it one of the five challenges.
Login page idea design
A playful visual concept where the character literally “arms” himself depending on the strength of the password.
As the user creates a stronger password, the character progressively equips himself with more powerful protection and armor. The stronger the password, the better prepared and more protected he becomes.
The idea turns password security into a simple and engaging visual metaphor , instead of showing abstract security levels, the user can immediately see how their password makes the character stronger and safer.
Very cool, Anna!
Weekend fun 😺. The new MacBook Pro has a Dynamic Island, and I kept wondering: what if that little pill was where your AI agent lived?
Try it live: https://lab.behzad.me/agent-mew/
So I spent the weekend prototyping Agent Mew. You drop a file on the notch, give it a task, and it quietly works up there while you keep doing your thing. It shows progress in the wings, asks a quick question when it needs one, and always waits for your OK before doing anything that leaves your Mac, like sending an email.
A few things I explored:
- Progress that stays out of the way, readable at a glance
- Questions as one tap, not a chat window
- Approval cards for anything with real consequences
- Paused and stuck states that tell you what to do next
- A small animated cat, because agents should have some personality
Approval cards for anything that leaves the Mac is the right line to draw. Does the card show the full email before you tap OK, or a short summary? I'd lean toward full text for anything going to another person.