Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Parsera: LLM-Powered web scraping
Learn how to use the Parsera library to extract structured data from any website by providing a URL and data description, no scraper code needed.
Parsera is a Python library for lazy scrapping :) Tired of writing custom scrapers for each site, I built an LLM-Powered scraper that can extract data from any page. Instead of coding, you provide the URL and description of the data you need and receive a table with all the data in return.
Python library for LLM-powered web data extraction via Playwright.
LLM-powered Parsera extracts structured web data using natural language prompts.
- ParseraParsera is the AI-powered data extraction engine: input a URL and a natural language prompt to instantly generate structured data at scale.Parsera delivers high-efficiency web data extraction, leveraging Large Language Models (LLMs) to transform any URL and a simple prompt into structured output (JSON, CSV). The core value proposition is no-code scraping: users bypass complex selectors and brittle code maintenance. For large-scale operations—like extracting hundreds of product pages or monitoring competitor pricing—Parsera's AI Agent generates reusable Python scraping scripts. This generated code eliminates LLM hallucinations, drastically cuts operational costs, and boosts extraction speed, ensuring reliable, enterprise-grade scalability. Integration is straightforward via API or through platforms like Zapier, n8n, and Apify.
- PythonPython: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .
- GitHubHost Git repositories and enable massive-scale collaboration (pull requests, issue tracking) for over 100 million developers.GitHub is the world's dominant web-based platform for Git repository hosting and collaborative software development. Built on Linus Torvalds' Git version control system, the platform facilitates 'social coding' by providing essential tools like pull requests, forking, and issue tracking. It currently serves over 100 million developers, managing a massive ecosystem of public and private codebases. Microsoft acquired the company in 2018 for $7.5 billion, solidifying its role as the central hub for open-source and enterprise-level version control.
- Web scrapingDeploy automated bots to fetch, parse, and structure vast datasets (e.g., prices, reviews) from public web pages at scale.Web scraping is the automated extraction of data from websites using specialized software (bots or spiders). This process involves sending an HTTP request, receiving the HTML, and then parsing that code to isolate target data points: product prices, contact information, or news headlines. Developers frequently use Python libraries like Scrapy or Beautiful Soup to build these scrapers. The output is structured data, typically in CSV or JSON format, enabling high-value applications like competitive price monitoring across 500+ e-commerce sites or large-scale market research aggregation. We leverage this technology to turn unstructured web content into actionable business intelligence.
Related projects
Genaicode - programming on steroids
Poland
Live demo of Genaicode, an AI code generator, modifying a personal game in real time and covering latency,…
Evaluating a Medical Assistant
Poland
Learn how we built a two‑tier evaluation framework for a medical transcription AI, using LLM‑driven factual checks, style…
Practical demo challenges in creating LLM-based consumer products
Poland
Explore real-world obstacles and solutions when integrating large language models into consumer products, covering design, deployment, testing, and…
CompileBench Eval: Do You Need AGI to Compile Google Chrome?
Poland
The talk introduces CompileBench, an evaluation that requires LLMs to compile real open-source projects, detailing methodology, challenges, results,…
Claude Don't Code
Poland
Demonstration of using Claude Code as a terminal assistant for tasks like certificate renewal, CSV analysis, Docker debugging,…
Efficient data extraction from documents for data analytics and process automation
Poland
Explore Arctic‑TILT, a 0.8 B‑parameter model that outperforms GPT‑4 in document processing, enabling efficient data extraction for analytics and…