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
I'm thoroughly frustrated by the prevalence of accounts on Contra that use AI to reply to posts. And I don't get it. The entire point of this community is to share what you're working on and engage authentically with other creators and designers. So I'm genuinely confused as to what folks think the benefit is there? All I get from it is the sense that you either can't or aren't willing to think for yourself. So what're you doing on a platform that's built for /creatives/?
Thanks Madi, I'm really glad to hear 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
Related posts
Is AI finally good enough to shoot a product demo on its own, or human touch is still needed?
I generated a 20s product demo with Seedance 2.5 in a single take providing it with one product image reference and an example video transcript (posted in the comments). Do you disclose to a client how much AI is involved, or just let the result speak for itself?
Is AI finally good enough to shoot a product demo on its own, or human touch is still needed?
I generated a 20s product demo with Seedance 2.5 in a single take providing it with one product image reference and an example video transcript (posted in the comments).
Do you disclose...
Just posted a new case study on Contra.
A 60-second promo for Ulta AI by Ultahost, a chatbot that runs a server through plain conversation. Script, storyboard and animation, all built around the real product UI.
Check it out
Let me know what you think💭😍
Just checked it out - this is fire Blahomyr! 🔥 A 60-second promo built around real product UI with script, storyboard and animation - that's how you do it! Love the "endless panels" concept, super clean execution in After Effects. Ulta AI's conversational server management feels so intuitive in your promo!
Why AI Agent Demos Break in Production
An AI agent demo only has to work once, on a clean input, with you watching. In production it runs again and again on messy real inputs, and nobody's watching.
I've built AI into real products, from a repricing engine that runs 24/7 for a US Amazon seller to a voice automation platform for a company in Germany. These are the three things I put in place before any agent goes live:
1. Scoped tools, not open access
Give the agent a short list of actions it's allowed to take, each with its own limits, instead of raw access to your database or APIs. Anything that touches money, customers or deleting data needs a human to approve it.
2. A plan for when the model fails
Model calls are slow, they time out, and sometimes they return something that makes no sense. Run agent work in background jobs with timeouts and retries, check the output before acting on it, and hand the task to a person when it still can't be trusted.
3. A log of every decision
Store every input, tool call and output. When the agent does something strange (and at some point it will), you can see exactly why and fix it instead of guessing.
None of this shows up in a demo. All of it decides whether the agent is still running a month later.
Planning an AI agent for your product? I offer a free build audit: calendly.com/roshaanali-business
