PINGDOM_CHECK

Extract Summit 2025 – Live from Austin

September 25 | AUSTIN, USA

Main Event

25th September 2025
9:15 AM

How to Make AI Coding Work for Enterprise Web Scraping

Iain Lennon | CPO @ Zyte & John Rooney | Developer Engagement Manager @ Zyte
Enterprise-scale scraping demands control, reliability, and engineering discipline that no-code AI tools can’t match. AI coding offers hope, but often fails to deliver effective spiders. This talk shows how to bridge the gap and meet the needs of professional web data teams.
25th September 2025
9.45 AM

Why AI Agents Struggle with Web Scraping (and How to Help Them)

Iván Sánchez | Senior Data Scientist @ Zyte
Discover why web scraping is uniquely hard for AI agents. This talk explains the key challenges that cause them to fail and offers practical strategies and tools to make agents more resilient in real-world scraping.
25th September 2025
10.30 AM

The Technical Reality of Processing 10% of Google’s Global Search Volume

Julien Khaleghy | Founder & CEO @ SerpApi
Learn how SerpApi scales scraping Google using geolocated proxies, headless browsers, and adaptive parsing pipelines to reliably extract search results across languages, devices, and experiments while converting unstable HTML into clean, usable data.
25th September 2025
11.30AM

You Might Want to Reconsider Scraping with LLMs

Jerome Choo | Director of Growth @ Diffbot
See how LLMs impress with web scraping demos yet collapse in accuracy, reliability, and cost at scale. This talk unpacks when to use LLMs, traditional methods, or hybrids—through rapid demos and a takeaway guide for real-world data expertise.
25th September 2025
12.00PM

Do You Really Need a Browser? Rethinking Web Scraping at Scale

Sarah McKenna| CEO @ Sequentum
VC money is rushing into scraping browsers and related tech—from new startups to big moves like Perplexity’s Chrome bid. But is this real need or hype? This session explores trade-offs, market shifts, and Sequentum’s view on where browsers belong.
25th September 2025
12.30 PM

Web Scraping as Social Practice: Balancing Ethics and Efficiency in a Data-Hungry World

Rodrigo Silva Ferreira | QA Engineer Posit PBC
Scraping is never just technical. This talk unpacks the ethics of data access, exploring how APIs, public content, and code collide in a high-stakes negotiation between openness, compliance, and responsible extraction.
25th September 2025
2:00 PM

Balancing Innovation and Regulation in Data Scraping

Sanaea Daruwalla | Chief Legal & People Officer @ Zyte
Learn how to use web data without crossing legal or ethical lines. This talk covers the changing rules around scraping, AI, and case law and gives simple strategies to stay compliant while still innovating and gaining business value.
25th September 2025
2:30 PM

Building Blocks of a Web‑Scraping Business

Victor Bolu | CEO @ Webautomation
Discover how scraped data evolves into recurring revenue by mastering cost per scrape, churn triggers, support load, pricing tests, and daily KPIs—giving you a clear, actionable blueprint to launch and scale a sticky, profitable scraping business.
25th September 2025
3:30 PM

99 Problems but a /24 Ain’t One (Except When It Is)

Ovidiu Dragusin | Servers Factory
Dive into the unpredictable world of IPv4 brokerage, geolocation mismatches, crisis response, and IP sourcing strategy plus how demand from AI scraping pushes infrastructure, databases, and compliance to their absolute limits
25th September 2025
4:00 PM

Data-Quality Framework for User-Submitted Financial Documents

Egor Panfilov | Team Lead @ Truv
Income verification relies on accurate data from paystubs, W-2s, and bank transactions. This talk shows how to build a data-quality framework using cross-referencing, reconciliation checks, and LLMs as assistive validators.