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
AI is moving from answers to action.
Assistants answer questions.
Agents connect to tools, decide, and run multi-step workflows.
The shift:
ASK → ANSWER
to
UNDERSTAND → DECIDE → ACT
The useful question isn’t “Can AI help my business?”
It’s “What work can an agent actually own — and how do we measure it?”
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
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 🤖📊
Everyone loves to say AI makes creative work feel impersonal but I found the uses that actually save time without replacing my creative expertise.
Here's what's been working for me:
✍️ Copy and emails: I write the base, AI helps me polish and tighten it
🎨 Concept and moodboard copy: same approach, I write the core idea, AI helps shape the language for presentations
📦 Mockups: AI speeds up creation so I don't spend hours looking for the right .psd online
The key has been using it to speed up the boring parts so I can focus on the creative bits.
What's an AI use in your workflow that actually made things better, not just faster?
Starting with your own draft is close to how I use it on builds. I give AI the page and a short checklist, then use what it catches to tighten the work before I ship.
🔥 TalentFilter AI — AI-Powered Candidate Screening
TalentFilter AI is an AI-powered hiring application designed to help recruiters and hiring teams evaluate candidates faster and focus on the people who best match each role.
In Phase 1, I built the core hiring workflow: users can create and manage job openings, add candidates and CVs, automatically analyze candidate profiles with AI, generate match scores and hiring recommendations, and quickly identify the strongest candidates through a ranked dashboard and AI hiring insights.
The goal is simple: turn a pile of resumes into a clear, actionable shortlist.
Phase 2 will expand TalentFilter AI into a more complete recruiting workspace, including deeper candidate profiles, improved AI-generated interview questions and hiring insights, candidate pipeline/status management, stronger analytics, workflow automation, and a more polished end-to-end recruiter experience.
Built with: Bubble, AI integrations, workflow automation, dynamic data, and responsive UI.
