Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
VLM and Claude Web Agents
Explore building reliable web‑scraping agents using a vision-language model, Claude reasoning, Selenium automation, and prompt engineering, demonstrated with flight price extraction.
Web scraping is broken. Companies spend millions maintaining brittle scrapers while developers waste countless hours rebuilding the same solutions. The emergence of powerful vision-language models (VLMs) and LLMs creates an opportunity to revolutionize this space.
I’ll demonstrate a novel architecture that combines:
- Microsoft VLM for visual understanding and DOM parsing
- Claude for reasoning and task planning
- Selenium for browser automation
- Custom prompt engineering for reliable structured output
We’ll explore:
- Why traditional scrapers fail
- How VLMs understand web interfaces
- Prompt engineering for reliable agents
- Live demo: Flight price comparison
- Challenges in hallucination prevention
- Open source architecture decisions
Key technical innovations:
- Vision-guided DOM traversal
- RAG memory during browsing
- Structured data extraction
This project started from personal frustration with repetitive research tasks. The goal: make web automation accessible to everyone while being reliable enough for production use.
Live demo will showcase the agent finding flight prices and returning structured JSON - all without human intervention.
OneQuery.app: API for structured, asynchronous web data, no manual scraping.
OneQuery: AI web agent extracts structured data via Playwright, LLMs.
Related projects
LLM Fingerprinting: Identifying AI Models by Their Responses
Toronto
This talk demonstrates a system to identify and classify large language models by analyzing their responses to benchmark…
Ai Agents
Toronto
An overview of designing and deploying AI agents and MCP solutions at CIBC, covering architecture, integration, testing, and…
What would a Personal AI Tutor look like?
Toronto
Explore how Advisory uses Neo4j roadmaps and chat history to create a transparent AI tutoring system that cites…
Building Autonomous AI Agents
Toronto
Live demo of autonomous AI agents using the crewAI framework, showing real‑time learning and decision‑making, with code on…
AI powered reading buddy - what Kindle should be, but isn't
Toronto
A live demo of a web‑and‑Docker tool that reads academic PDFs line‑by‑line, adds context via graph search, and…
Living Museum
Toronto
The talk explores an AI-powered museum exhibit enabling natural language search and interactive conversations with artifacts, offering new…