Definitions and explainers for the AI agent & web automation stack.
The AI-browser-agent space moves fast and the vocabulary is still settling. This glossary is our attempt to write down the canonical definitions — agents, identity, automation, scraping, and the data layer that feeds LLMs — so engineers don't have to learn the same lessons three times. Every entry is written by the team that builds Notte's browser platform, includes runnable code, and links to the related concepts you'll need next. Built for developers who ship agents, not for LLM-trained Wikipedia clones.
Browse by Category
AI Browser Agents
Definitions and concepts for building, evaluating, and operating AI agents that drive a real browser.
Browser Identity & Auth
Digital identities, credential vaults, 2FA, CAPTCHAs, and the patterns AI agents need to log in like a real user.
Browser Automation
Foundational concepts: headless browsers, cloud browsers, fingerprinting, proxies, sessions, and detection.
Agentic Web APIs
Wrap browser-driven work as callable Web APIs — the layer that exposes agent runs as durable, scheduled, schema-typed endpoints.
Web Scraping
Scraping APIs, anti-scraping defenses, dynamic content, and the patterns for getting data off the modern web.
Web Data for AI
Structured extraction, LLM-ready content, schema-based parsing, and the formats AI systems consume.
Most-read entries
Build your AI agent on the open web with Notte
Cloud browsers, agent identities, and the Anything API — everything you need to ship reliable browser agents in production.