---
title: "Dense Slides: The rise of the agentic economy on the shoulders of MCP — Jan Curn, Apify"
category: "slides"
video_id: "blW-lSd5CYQ"
sourceLabels: ["Captured video frames", "Local OpenCV slide-region detection"]
---

# Dense Slides: The rise of the agentic economy on the shoulders of MCP — Jan Curn, Apify

## Source Video
[The rise of the agentic economy on the shoulders of MCP — Jan Curn, Apify](https://www.youtube.com/watch?v=blW-lSd5CYQ)

## Method
This deck is slide-only. The existing captured video frame set supplies candidate frames, then local OpenCV rejects sponsor/title/speaker-only frames, crops visible slide surfaces, deduplicates, and saves the cropped slide images.

## Cropped Visible Slides
![[assets/dense-slides/blW-lSd5CYQ/slide-001.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/blW-lSd5CYQ/slide-001.html)
- AI slide classifier: `title_card` confidence `0.98`
- Text source: agent_vision.

Slide text:

> How does intelligence emerge in markets?

![[assets/dense-slides/blW-lSd5CYQ/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/blW-lSd5CYQ/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.

Slide text:

> So how will general intelligence emerge in computing systems?

![[assets/dense-slides/blW-lSd5CYQ/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/blW-lSd5CYQ/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: advanced OCR `rapidocr-live/bright-screen/opencv-adaptive`.
- OCR decision: ready — Dense product-card grid with small text across multiple tiles.

Slide text:

> Apify runs a marketplace of 5,oo0 Actors
> apify/website-content-crawler Website Content Crawler.? Google Maps Emall Extractor lukaskrlvka/google-mags-with-cont- Instagram Scraper... apify/instagraa-scraper
> feed Al models, LLM applications, vector databases, or RAG pipelines. The Actof... Crawl websites and extract text content to Extract Googie Maps contact detalls. Scrape details and get emall addresses, website,. websites of Google Maps places for contact comments. Get data from Instagram using.. proflies, places, hashtags, photos, and Scrape and download Instagram posts,
> ) Aplfy % 42.4k ☆ 4.6 0 Lukas Kflvka % 22.7k ☆ 4.7: C Apity 83.1k 4.3
> No Rate-Llmits: apidojo/twitter-scraper-lite Twittor (X.com) Scraper Unlimited: Facebook Posts Scraper apity/faccbook-posts-scraper clockworks/frce-tiktok-scraper TikTok Data Extractor
> solution available. Our enterprise-grade.... most comprehensive Twitter data extractlon Introducing Twitter Scraper Unlimlted, the.: and profiles. Get post URl, post text, page. Extract data from hundreds of Facebook posts from one or multiple Facebook pages User profles Including posts, total lkes.-. Extract data about videos, users, and channels based on hashtags or scrape fu!
> oa dv& 2 2.8k ☆ 4.5 D) Apify. 19.9k ☆4.5 Clockworks % 23.9k ☆ 4.7

![[assets/dense-slides/blW-lSd5CYQ/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/blW-lSd5CYQ/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: advanced OCR `rapidocr-live/left-72/opencv-adaptive`.
- OCR decision: ready — UI screenshot with many small labels, metrics, and metadata fields.

Slide text:

> GoogleMapsScraper
> Try tor tree
> compass/crawler-google-places O Developed by Compass Maintained by Apify
> Extract data from thousands of Google Maps locations and businesses. Get Google Maps
> schedule and monitor runs, or Integrate with other tools. details, images, contact info, opening hours, location, prices & more. Export scraped data
> ★★*★☆ 4.2 (56): (: 0 Pricing Payper event |Q 1100: 1 % Monthly users 8.2k Runs sl
> Response time 4.5 days I G Last modified 3 hours ago:
> Lead generation

![[assets/dense-slides/blW-lSd5CYQ/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/blW-lSd5CYQ/slide-005.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: none.
- OCR decision: ready — Code slide with small monospaced text and tabs.
![[assets/dense-slides/blW-lSd5CYQ/slide-006.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/blW-lSd5CYQ/slide-006.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.

Slide text:

> Use Actors from AI agents using MCP

![[assets/dense-slides/blW-lSd5CYQ/slide-007.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/blW-lSd5CYQ/slide-007.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: advanced OCR `rapidocr-live/bright-screen/opencv-adaptive`.
- OCR decision: ready — Dense small screenshot text with bullets, status message, and UI chrome; OCR will recover details better than direct transcription.

Slide text:

> Process Detalls::
> .Navigatlon: Successfully loaded the Al Engineer World's Fair homepage
> . Form Location: Found the subscription form with placeholder *your@work.email"
> Emall Input: Successfully entered jan@apify. con: into. the email field
> Form Interaction: Clicked the submit button (arrow icon) multiple times:
> Current Status:
> The form shows a validation error: "Invalid Emall Address. Please use a valld email
> address."
> *This appears to be a cllient-side validation issue wit:
> Claude doos not have internet sccoss enobled. Enable web search for up to date and accurato links.
> . Reply to Claude...
> Q Researth. ntra: Claude Sonnct 4


Classification audit: `raw/sources/slide-ai-classification/dense/blW-lSd5CYQ/audit.json`