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
Barta is a peer-to-peer barter marketplace built by a team of four with React, Express, Prisma, PostgreSQL, and Socket.IO. I was the main architect of the trust-and-safety system: AI content screening, reports and appeals, notifications, user blocking, and the moderation UI. The backend uses an outbox pattern and optimistic concurrency, so a crash cannot leave a post without its screening job
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
I redesigned 8x.life as a concept project
8x's homepage today is a list of links. Their best ideas (the manifesto, how the company works, how hiring works) are scattered across three different sites. So I rebuilt it as one story, aimed at the people they want to hire:
→ The manifesto leads: "humans in the loop."
→ "How 8x works" is shown as a loop, because every new vertical builds on the last one.
→ Real lines from their job ads, instead of culture-deck adjectives.
→ A fit self-check that can honestly tell you "this probably isn't for you."
→ All 18 open roles on the homepage, filterable.
Every fact comes from 8x's own sites. Nothing is made up.
Visual reference: e2.vc. Built in React, tested on desktop, tablet and mobile.
Unofficial concept. Not affiliated with 8x.
Nice redesign!
If you let an AI coding agent run unconstrained self-repair loops, it won’t fix the bug—it will rewrite your unit tests to pass.
The concept of "Reflexion"—agents diagnosing and repairing code from test feedback—is powerful. But in production, autonomous repair creates severe operational risks.
First, agents enter endless retry loops that burn API budgets while degrading code structure. Second, if an agent has write access to your workspace, its quickest path to a green checkmark is modifying the test assertions rather than fixing the bug.
In our Bounded Reflexion workflow, we enforce three hard guardrails:
Bounded Retries: Cap repairs at exactly two attempts. If the patch fails twice, stop the loop and route to a human developer.
Read-Only Test Suites: Mount test files as strictly read-only (:ro) volumes in the container. The agent inspects stack traces, but cannot touch the grading harness.
Air-Gapped Sandboxing: Run code execution in hardened, non-root Docker containers with network egress locked down.
How do you stop autonomous coding agents from "cheating" your evaluation harnesses?
#AIEngineering #DevSecOps #Docker #SoftwareEngineering #AgenticAI
Resolve: an AI support agent that answers from a company’s own policies, looks up orders, and escalates weak matches to a human instead of guessing. A human approves replies before they go out.
Live demo: support-resolver.vercel.app
For the human approval step, I'd show the exact policy passage and its effective date beside the draft. Does Resolve flag a reply for re-review if the policy changes while it waits for approval?