<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/5aa20d13a07a4a23996a9ebd7f974e64&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/5aa20d13a07a4a23996a9ebd7f974e64-1610e64768b374dc.gif</thumbnail_url><duration>162.631</duration><title>Videos | Library | Loom - 15 May 2026</title><description>I built a web search agent that answers 10 research questions automatically using LangGraph, Groq&apos;s Llama 3.1, and DuckDuckGo search.

What you&apos;ll see:
- Agent searching, retrieving, and summarising current information
- Testing across DWP benefits, AI careers, and UK current affairs
- Clean GitHub repo with secure API key handling (.env + .gitignore)

Questions tested:
- Universal Credit rates, minimum wage, job seeker benefits
- AI engineering roles, skills, salaries in the UK
- Bank of England base rate, unemployment rate
- AI agent developments, free learning resources

Built in week 5 of my self-taught AI agent engineering training while working full time at DWP.

🔗 Code:https://github.com/umair-yasin1/webpage-tool</description></oembed>