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
Commitments made in meetings used to live in three places: someone's notes, someone's inbox, and someone's memory.
So, I built one tracker. Every action item gets an owner, a due date, and the meeting it came from, captured before the room clears rather than reconstructed later. One weekly review pass. Automatic escalation at seven days past due.
The point wasn't the spreadsheet. It was that follow-through stopped being something people assumed and started being something you could see. illustrative recreation. No real records, agency or client.
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
Habit tracker mobile app UI design + Motion ❤️
wow
Open almost any app with a stats screen and you hit the same miss. It counts something, then leaves you to work out why you should care.
"400 hours" and "400 hours reclaimed" are the same number. One reads as a metric. The other is a small win the user gets to own.
Most products stop at the count. Sessions, streaks, totals, all true and all forgettable.
Do that work for them. Say what the number bought them. Time back, progress made, a habit they're keeping.
Leave the user to supply the meaning and most won't. They close the screen, and the one thing that might pull them back tomorrow closes with it.
This is so true. A number means a lot more when you show the actual win behind it.
This portfolio sample shows how I evaluate AI agents and automated workflows to find reliability problems, broken logic, and weak edge-case handling. I review whether the system completes the intended task, uses tools correctly, follows instructions, handles ambiguity, and produces an output that can actually be trusted.
The work focuses on identifying failure points before they become real user problems, including incomplete task execution, incorrect assumptions, workflow dead ends, hallucinations, and verification gaps. This is a portfolio demonstration of my AI agent evaluation and red-teaming work. No confidential client information is included.
Thorough breakdown! Robust edge-case handling and reliability checks are definitely the trickiest part of building reliable AI agents 🤖📊