Automating Web Workflows with LLMs
summary
Claims that Apify turns natural-language prompts into repeatable web workflows, using Apify's AI web agent with Python/JS SDKs and open source libraries like crawly; demos show filling forms and extracting pricing into a schema and rely on a screenshot + set of marks vision mapping. Approach uses a limited action API (click, go to URL) not raw code generation. Notes practical limits: context window, captchas, cookie modals, flaky LLM determinism and performance—demo works but reliability and speed remain concerns.
AI-written summary · about
chapters (8)
- 0:00Automating web workflows
- 5:27Manual automation fails
- 7:58LLM automation agent
- 16:33Web automation challenges
- 22:40Form filling demo
- 25:52Data extraction demo
- 27:17AI web agent demo
- 38:13Question and answer session
related talks
01h 10mTeach an LLM to Navigate the Web
35mBuilding LLM-based Agents
24mBots & Humans: Maintaining AI agent and automation in an AI-bot web
01h 39mMastering LLMs: From Prompt Engineering to Agentic AI
01h 28mBuilding LLM Agents Made Simple a
40mAgentic AI: The Next Evolution of Automation
47mCan You Trust Your ChatBot: Techniques for Testing LLM Responses
49mNext-Gen Documentation with AI