{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/5aa20d13a07a4a23996a9ebd7f974e64\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/5aa20d13a07a4a23996a9ebd7f974e64-1610e64768b374dc.gif","duration":162.631,"title":"Videos | Library | Loom - 15 May 2026","description":"I built a web search agent that answers 10 research questions automatically using LangGraph, Groq's Llama 3.1, and DuckDuckGo search.\n\nWhat you'll see:\n- Agent searching, retrieving, and summarising current information\n- Testing across DWP benefits, AI careers, and UK current affairs\n- Clean GitHub repo with secure API key handling (.env + .gitignore)\n\nQuestions tested:\n- Universal Credit rates, minimum wage, job seeker benefits\n- AI engineering roles, skills, salaries in the UK\n- Bank of England base rate, unemployment rate\n- AI agent developments, free learning resources\n\nBuilt in week 5 of my self-taught AI agent engineering training while working full time at DWP.\n\n🔗 Code:https://github.com/umair-yasin1/webpage-tool"}