"Abdullah Usman team on AMD AI League Hackathon"

WebScout AI — Evidence-First Intelligent Web Retrieval Agent WebScout AI is an agentic web research system built for the AMD AI League Match 4: Intelligent Web Information Retrieval. It transforms natural-language queries into structured research workflows, retrieves multi-source information, verifies evidence, and generates concise answers with traceable citations. The Problem Traditional AI assistants often generate convincing answers without reliable grounding. Researching across fragmented, complex, or deeply navigated web pages makes finding accurate facts challenging. Users require transparency and verified evidence over unsupported AI output. Our Solution WebScout AI leverages LangGraph to orchestrate an end-to-end pipeline: query analysis, source discovery, navigation, content extraction, evidence ranking, verification, and answer generation. TinyFish handles web search and retrieval, while configurable LLM providers (OpenRouter, Gemini, NVIDIA-compatible APIs) execute structured extraction. Key Capabilities Agentic Execution: Natural-language research with bounded agent steps. Smart Web Discovery: Web search and deep navigation powered by TinyFish. Evidence Verification: Ranks evidence and verifies exact-source quotations. Traceable Citations: Generates answers linked directly to sources. Conflict & Hallucination Guardrails: Detects unsupported claims and safely abstains when evidence is missing. Flexible Configuration: Supports customizable LLMs, timeouts, and resource limits. Production Ready: FastAPI backend, lightweight frontend, and Docker containerization. Technical Stack & Validation Built with Python, FastAPI, LangGraph, LangChain, TinyFish, Pydantic, and Docker. Its architecture strictly separates retrieval from verification to minimize hallucinations. The system passed 64 automated tests and 26 offline evaluation cases, successfully demonstrating live end-to-end research via TinyFish.