Portfolio showcasing projects and research. Zola 2026-04-04T00:00:00+00:00 https://blog.sooraj.fun/tags/ai-agents/atom.xml 2026-04-04T00:00:00+00:00 2026-04-04T00:00:00+00:00 Unknown https://blog.sooraj.fun/projects/moderix/ <p>Autonomous AI agents for scalable Trust &amp; Safety content moderation in OpenEnv environments, featuring high-performance routing.</p> <h3 id="why-it-exists">Why it exists</h3> <p>Built for the Meta x Scaler x PyTorch hackathon. We set out to solve the massive scaling challenges of content moderation by creating autonomous trust and safety agents that run locally.</p> <h3 id="how-it-works">How it works</h3> <ul> <li>Implements specialized moderation routing agents built on PyTorch.</li> <li>Packages local inference environments cleanly inside <strong>Docker</strong> containers.</li> <li>Orchestrates multi-agent handoffs for text and visual content evaluation.</li> <li>Serves low-latency agent models deployed on <strong>Hugging Face Spaces</strong>.</li> </ul> <h3 id="what-happened">What happened</h3> <p>We wrote the entire codebase in an intense 5-day hackathon sprint. Near the deadline, we ran our test suite of 26 test cases: 23 failed, and only 3 passed. It was a chaotic, eye-opening experience. We debugged until the final hours, learned a massive amount about agent stability, and managed to get the system operational.</p> <h3 id="what-i-d-change">What I'd change</h3> <p>I'd move the agent routing decision matrix from rules-based weights to a lightweight, fine-tuned classification model to handle nuanced semantic contexts more dynamically.</p> <h3 id="links">Links</h3> <p><a href="https://github.com/whysooraj/Moderix">GitHub</a></p>