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
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
Love how each agent has its own identity and personality. Really nice work! 🔥
Why my AI never sends anything without asking me first
Most people who try AI give it one long prompt and hope. It works for a day, then it guesses, drifts, or does something nobody asked for.
I build it the other way round. Every AI employee I set up gets a job description, rules, a daily checklist and test tasks it has to pass – like a new hire. And before anything goes out, there are five steps: draft → safety check → exact preview → my yes → logged.
One yes = one action. Payments, passwords and deletes never go to the AI at all.
If you’re new to AI and want to set this up in your own Claude or Grok account, my first lesson walks you through it step by step.
honestly the only sane default. one bad auto send and the trust is gone
A great question asked by Huzaifa Tahir on AI Agent Standards... everyone must notice this.
contra.com
Huzaifa Tahir’s Work | Contra
View Huzaifa Tahir’s work on Contra. The Independent-first, commission-free freelance marketplace shaping the future of work.
The OpenSandbox piece is what stands out to me, because safe execution of agent actions matters most when the agent can touch patient-adjacent systems. In healthcare I'd want every tool call scoped to a narrow permission set and logged, so interoperability never quietly widens...