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
Reliable AI agents need a clear boundary before they act.
Raposa Aval is a human-approval layer for AI agent actions. It connects MCP and API-based tool calls with explicit review, approval or rejection, and auditable records.
My work on Raposa Aval focuses on controlled execution rather than unrestricted automation.
The project reflects how I approach AI systems: agents should be useful, while sensitive actions remain observable, reviewable, and accountable.
Project: https://raposa.group
More work: https://contra.com/darius_ceponas_77ewu7nj
raposa.group
Raposa — Human-in-the-loop approval layer for AI agents
Human approval before an AI agent makes a payment, deploy or sends comms — with a verifiable, hash-chained audit trail. Agent approval layer for autonomous agents. EU / GDPR.
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
Feels like a lot of companies are trying their luck with AI instead of hiring designers right now.
I think it's going to backfire on them in a few months.
Trying to stay optimistic about it.
I can't wait for them to start hiring designers again. No matter how good AIs are, Human Intelligence will always supercede it.
Thinking about making a course on how I actually work with AI agents.
Not prompts.
The rules, skills and checks that make the agent build things the way my repo wants.
Would that be useful to anyone?
Yes please. The rules and checks part is what nobody teaches. Prompt tips are everywhere, repo setup isn't.
Designed a modern AI Research Agent SaaS Web App.
A clean white workspace with soft gray panels, simple icons, and calm blue accents for a focused and professional first impression.
A chat thread where the agent shows its plan step by step, live progress for parallel tasks, and a smart sheet that fills itself row by row with cited sources make complex research feel clear and trustworthy. A simple sidebar, credits tracker, and familiar table tools keep the whole app easy to use.
Great work!