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 agents are becoming more autonomous — and now they need their own safety infrastructure.
NVIDIA has introduced the Open Agent Safety Platform, designed to help organizations control what autonomous AI agents can access and do.
The platform includes:
• OpenShell — a sandboxed environment that restricts an agent's access to systems and data.
• Sentry — a monitoring layer designed to detect and stop potentially dangerous agent behavior.
Why does this matter?
AI is moving beyond chatbots. Agents can now browse websites, interact with software, execute tasks, and make decisions across multiple steps.
That creates a new challenge:
How do we give AI more autonomy without giving it unlimited access?
The next phase of AI may not only be about building more capable models. It may be about building the infrastructure that keeps those models controlled, observable, and secure.
This is one of the areas I’m particularly interested in: AI agents, automation, and the infrastructure required to make autonomous AI useful in the real world.
#AI #ArtificialIntelligence #AIAgents #NVIDIA #Tech #Automation #AIEngineering #FutureOfAI
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
My AI assistant runs all day. The expensive model only does the thinking.
Most requests need no AI at all. "Call me in 30 minutes" is handled by plain code. Reminders, schedules and limits are code too.
Short tasks like sorting and scoring go to fast models on a free tier.
The big model only gets planning and long conversations, where it actually has to think.
If it hits a limit, a backup model answers instead of the app going silent.
If your AI app's bill keeps growing, check what really needs the big model.
What does your app send to the most expensive model?
• Oct 16
Same pattern holds in outbound tooling. Filtering, dedupe and enrichment lookups are plain code. The model only writes the first line once the row is already verified. Cuts cost and the weird outputs.
Picture a consultant who takes 8 sales calls a week.
After each one comes the same routine: replay the recording, write notes, update the pipeline sheet, write the follow-up email. Call it 30 minutes a call. That is 4 hours a week, and on busy days the follow-up slips to tomorrow.
I built an n8n workflow that takes that routine away:
→ Fireflies records and transcribes the call
→ As soon as the transcript is ready, AI writes a summary, the open questions, the next step and whether the prospect is ready to go ahead
→ A follow-up email that fits that outcome is saved in Gmail drafts, addressed to the person on the call
→ The call is logged in Google Sheets and the notes land in your inbox
Nothing is sent automatically. You read the draft, change a line if you want, and press send.
For that consultant, 4 hours of admin a week turns into a few minutes of reading, and every prospect hears back the same day.
I tested it on a real recorded client call and have submitted it to the n8n template library as a free template. If you want it set up for your business, send me a message.
AI can design websites. So why do startups still need designers?
AI knows what your product does.
But does it understand why your customers struggle with the problem it solves?
Does it understand their problems, doubts, and what makes them trust your product?
That's where human understanding matters.
As a designer, I keep noticing gaps in startup websites.
Unclear messages, weak value, and websites that don't connect with customers.
These aren't always visual design problems.
They're problems of understanding the customer.
AI can help us design faster. It can generate layouts, write copy, and explore ideas.
Someone still needs to understand the customer and decide what the website should communicate.
The goal isn't to choose between AI and designers.
It's to use AI as a tool while keeping human understanding at the center of the process.
Because a website shouldn't just look good.
It should make the right customer feel:
"This is exactly what I need."
If you're building a startup and feel your website could communicate your product better, I'd be happy to connect.
These aren't always visual design problems, they're problems of understanding the customer is the line that hits hardest, Nirooz. Unclear messages and weak value come from shallow understanding, not bad layouts. Well argued.