.png&w=256&q=75)
Asad Javed@Malik1x
3
Events attended
1
Submissions made
1 year of experience
About me
Asad Javed is a Pakistan-based AI engineer and entrepreneur building the next generation of intelligent, locally relevant automation products. As founder of Premium Logic, he focuses on designing agentic systems and WhatsApp-native AI experiences tailored to Pakistan's informal economy — combining PKR pricing, Roman Urdu/Urdu NLP, and mobile-first UX into products that work for real users on the ground. His engineering practice spans the full modern AI stack: multi-agent frameworks with Google ADK, Claude, Gemini, and DeepSeek; backend systems in FastAPI and n8n; frontend development in Next.js and Flutter; and vector/data infrastructure using Qdrant, pgvector, Firestore, and PostgreSQL. He works at the intersection of production engineering and applied AI research, with a clear emphasis on systems that ship and scale.
🤓 Latest Submissions
.png&w=828&q=75)
EthicsBoard AI — Multi-Agent IRB Review
Institutional Review Board (IRB) approval is the mandatory gate for any research involving human subjects — and today it takes six to twelve weeks of fragmented email review. A single overlooked consent clause restarts the clock. It isn't a knowledge problem; it's a coordination problem. EthicsBoard AI is a multi-agent IRB review platform built for Track 3 (Regulated & High-Stakes Workflows). Four specialist agents — Protocol, Ethics, Privacy, and a Committee coordinator — collaborate entirely through Band to review a research protocol end to end. Crucially, no agent calls another directly: every analysis, handoff, and decision flows through a single Band room via @mention routing, and that room becomes the tamper-evident, timestamped audit record regulators require. The workflow is genuinely non-linear. The Protocol agent classifies risk and routes the review (expedited vs. full board under 45 CFR 46). Ethics and Privacy then review in parallel, flagging deficiencies with exact citations — for example, missing written assent for minors (45 CFR 46.408) and a missing HIPAA Business Associate Agreement (45 CFR 164.308). Before any human is involved, the Committee challenges the Ethics agent on its most severe finding, and Ethics must defend whether it is blocking or resolvable by minor revision. Only then does the Committee invoke Band's add-participant service to bring a human IRB Chair into the same room for the final, legally binding decision. Each agent runs on a different framework — LangGraph, Pydantic AI, CrewAI, and FastAPI — powered by open and frontier models through Featherless AI and the AI/ML API. The result is a true coordination layer: four agents that communicate, share structured context, disagree, escalate, and defer to a human — making the collaboration visible, useful, and central.
19 Jun 2026
