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
Built for AWS's Agents for Humans hackathon (Good Neighbor Agents track), the challenge was to design an AI agent that reduces real operational burden for a nonprofit rather than just automating a demo task.
I build a program operations agent for Macknificient World (my nonprofit) using the Strands Agents SDK, focused on two concrete workflows: grant deadline tracking and lesson planning. The agent handles the repetitive admin work and only surfaces items that genuinely need a human decision.
Outcome: A working, publicly-documented agent (open-source repo, architecture diagram, full demo walkthrough) that gives a small nonprofit meaningful admin relief without adding oversight burden.
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
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
Join the Design Your Startup Challenge running from now until until September 25th ✨
*Available to U.S. designers only*
🚨 AI FEATURES DON’T CREATE RETENTION.
COMPOUNDING VALUE DOES.
Most AI note-taking apps compete on:
🎙 faster capture
📝 better summaries
🏷 smarter tagging
🔎 stronger search
Useful, yes.
But none of that guarantees users come back.
The bigger opportunity is when the product starts getting more valuable because the user has already used it before.
In this concept, AI doesn’t just process a note.
It notices:
→ which ideas keep returning
→ which topics appear across different contexts
→ which thoughts may deserve action
→ when an old note becomes relevant again
That changes the product from an archive into a system that learns from accumulated behavior.
And that creates a much stronger growth loop:
More input → more context → better resurfacing → higher perceived value → more input
That’s the kind of mechanic I’d test for retention.
📊 Product targets
• 30%+ faster capture flow
• 40%+ increase in resurfaced-note engagement
• 20%+ improvement in weekly return rate
• 2× higher note-to-action conversion
• 50% less manual organization
The interesting AI products won’t win because they generate more.
They’ll win because every interaction makes the next one more valuable.
👉 BOOK A MOBILE APP STRATEGY SESSION
https://calendly.com/asol_design/book-diagnostic-call-linkedin-clone
What I like most here is the idea of AI becoming more valuable with time, not just more capable in the moment. If every new note improves how older thoughts are connected and resurfaced, the archive stops being storage and starts becoming product intelligence
Created my own coffee brand! Even though I don't technically fit the requirements of this challenge, I really wanted to bring this concept to life. How do you like the result? ☕️✨
Nice work @Mila Visuals
