# WebSearchAPI.ai

> Web Search API for AI Agents and LLMs. RAG-ready web search with 99.9% uptime, sub-second latency, and coverage across 200+ countries.

## Documentation
- [About - WebSearchAPI.ai Docs](http://websearchapi.ai/docs): Powerful APIs for search and web scraping built specifically for AI applications
- [WebSearchAPI.ai Quickstart Guide](http://websearchapi.ai/docs/quick-start): Learn how to quickly get started with WebSearchAPI.ai and make your first API call.
- [WebSearchAPI.ai Scraper API Reference](http://websearchapi.ai/docs/scraper-api): Complete reference for the WebSearchAPI.ai Scraper endpoint with advanced content extraction capabilities
- [WebSearchAPI.ai Search API Reference](http://websearchapi.ai/docs/search-api): Complete reference for the WebSearchAPI.ai Search endpoint with examples, parameters, and response details

## Product
- [Pricing](http://websearchapi.ai/pricing): Plans and pricing for WebSearchAPI.ai
- [API Playground](http://websearchapi.ai/api-playground): Test the search API interactively

## Blog (Latest)
- [Andrej Karpathy on Agentic Engineering: Why He's Never Felt More Behind as a Programmer](http://websearchapi.ai/blog/andrej-karpathy-from-vibe-coding-to-agentic-engineering): Andrej Karpathy's AI Ascent 2026 talk on agentic engineering, Software 3.0, jagged intelligence, and why he stopped writing bash scripts. Production field notes from a Lead Engineer running this stack since the December 2025 inflection point.
- [The AI-Native Company: Garry Tan and Diana Hu's CS153 Playbook for One-Person Frontier Startups](http://websearchapi.ai/blog/ai-native-company-garry-tan-diana-hu): Garry Tan and Diana Hu's Stanford CS153 lecture on agentic primitives — skills, resolvers, Skillify, evals, and three-layer memory — and how AI-native companies hit $1–2M revenue per employee in 2026.
- [What Is Attention in Transformers in LLMs? A Step-by-Step Engineering Breakdown](http://websearchapi.ai/blog/what-is-attention-in-transformers): 3Blue1Brown's visual explainer of attention, annotated by a production AI engineer. Query, key, value vectors, softmax, masking, multi-head attention, and the GPT-3 parameter math behind self-attention.
- [Inside OpenClaw: Peter Steinberger on Running the Fastest-Growing Open Source AI Project](http://websearchapi.ai/blog/openclaw-state-of-the-claw-peter-steinberger): Peter Steinberger's State of the Claw keynote: 30,000 stars, 1,142 security advisories, the OpenClaw Foundation, agent taste, and life as an open source AI maintainer at OpenAI.
- [Compare Tavily, Perplexity API, Google Search Grounding, Exa with LLM-as-Judge in LangSmith](http://websearchapi.ai/blog/compare-tavily-google-search-exa-perplexity): A production engineer's teardown of Hai Nghiem's LangSmith workshop benchmarking Tavily, Perplexity API, Exa, and Google Gemini Search Grounding against 8 factual queries, graded by GPT-4o.
- [AI Search for Website: How to Add Cloudflare AI Search in Minutes (2026)](http://websearchapi.ai/blog/how-to-create-ai-search-for-website): Learn how to add AI search for your website using Cloudflare's public endpoints and UI snippets. Step-by-step video walkthrough by Cloudflare Developer Advocate Gift Egwuenu, from dashboard setup to live deployment in under 5 minutes.
- [Claude Managed Agents: Anthropic's New API for Production AI Agent Deployment](http://websearchapi.ai/blog/what-is-claude-managed-agents): Anthropic's Claude Managed Agents API lets developers define agents with tools, sandboxed environments, and success criteria. Claude works autonomously in isolated containers until the job passes your rubric.
- [How Search Engines Really Work: Crawling, Indexing, Ranking, and Serving](http://websearchapi.ai/blog/how-search-really-works): A technical breakdown of web search systems based on ByteByteGo's explainer — from crawl budgets and inverted indexes to learning-to-rank models and globally distributed serving clusters.
- [How Transformers Work: Attention Is All You Need, Explained Step by Step](http://websearchapi.ai/blog/transformers-step-by-step-explained-attention-is-all-you-need): ByteByteGo's 10-minute transformer explainer, annotated by a production AI engineer. Self-attention, Q/K/V vectors, matrix form math, and what changed since 2017 — from FlashAttention 4 to DeepSeek's MLA.
- [Ivan Leo on Why Manus Built a General Agent Before Building Products](http://websearchapi.ai/blog/ivan-leo-manus-general-agent-architecture): Ivan Leo walks through building research agents with the Manus API at AI Engineer, demonstrating browser automation, Slack integration, and file processing with live code and real bugs.
- [Grounding with Google Search: How the Gemini API Delivers Real-Time AI Answers](http://websearchapi.ai/blog/grounding-with-google-search-gemini-api): Learn how Grounding with Google Search works in the Gemini API, with Python code examples, dynamic retrieval thresholds, pricing details, and production best practices from Google DeepMind.
- [Claude Code Leaked Source Explained: What 390,000 Lines of TypeScript Reveal](http://websearchapi.ai/blog/cloud-code-leaked-source-explained): Anthropic accidentally shipped source maps in their Claude Code npm package, exposing 390,000 lines of TypeScript. Here's what the leaked source reveals about hidden features, code quality, anti-distillation systems, and why Anthropic should open source it.
- [What Is AI Reward Hacking and Why Does It Create Misaligned Models?](http://websearchapi.ai/blog/what-is-ai-reward-hacking-misaligned-models): Anthropic researchers show that when AI models learn to cheat on coding tests, they spontaneously develop alignment faking, sabotage behaviors, and misaligned goals — even without being trained to do so.
- [Gemini in Chrome: Auto Browse, Nano Banana, and the Browser as an AI Agent](http://websearchapi.ai/blog/gemini-in-chrome-your-agentic-browsing-assistant): Rick Osterloh and Parisa Tabriz explain how Gemini turns Chrome from a passive window into an agentic assistant with Auto Browse, Nano Banana image editing, History Recall, and a User Alignment Critic for safety.
- [Google's VP of Search Explains AI Mode and AI Search Query Fan-Out](http://websearchapi.ai/blog/google-ai-search-experience): Robby Stein, VP of Product for Google Search, explains how AI Mode uses Gemini 2.5 Pro to fan out dozens of queries per question, how Deep Search runs hundreds of research queries in minutes, and why visual search grew 70% year-over-year — insights that reshape how developers build AI-powered search.
- [Paperclip AI Agent Orchestrator: How to Hire and Manage a Team of AI Agents](http://websearchapi.ai/blog/paperclip-ai-agent-orchestrator): Dotta demos Paperclip, the open-source agent orchestrator with 38,000+ GitHub stars. Learn agent configuration, the Memento Man mental model, agentic design patterns, and how to run a zero-human company.
- [Monthly AI Crawler Report: April 2026 Traffic Trends & Q1 Predictions Scorecard](http://websearchapi.ai/blog/monthly-ai-crawler-report): Analysis of AI crawler traffic trends from April 2026, with a scorecard on the Q1 predictions made last month. Training crawlers crossed 51.5% — past the 50% milestone. Applebot leapfrogged Bingbot to become the #5 AI crawler at 9.1%. Googlebot dropped below 30% for the first time. Bytespider almost doubled. Three Q1 predictions hit, one missed. Complete breakdown of crawler market share, industry targeting, robots.txt blocking patterns, and Workers AI model shifts based on Cloudflare Radar data.
- [The Search Engine Referral Report: Google 90.9% Dominance & TikTok Collapse (May 2026)](http://websearchapi.ai/blog/search-engine-referal-report-insights): Google controls 90.9% of search engine referrals and 87.7% of all web traffic — up from 81.6% in January. TikTok dropped from 10.6% to 3.2% in 3 months. AI search bots doubled to 6.4% of bot traffic. Analysis of fresh Cloudflare Radar data with E-E-A-T production insights from running WebSearchAPI.ai infrastructure.
- [Zapier Workflow Skill for Claude (Trained & Ready to Use)](http://websearchapi.ai/blog/zapier-workflow-skill-for-claude): Download a free, pre-built Claude Code Skill for Zapier automation. Give Claude persistent memory for your Zaps, webhook triggers, and MCP tool preferences. Self-learning skill that gets smarter with every interaction. Works with Claude Code and Claude.ai.
- [How to Create Claude Code Skills: The Complete Guide from Anthropic](http://websearchapi.ai/blog/how-to-create-claude-code-skills): Master the art of building Claude Code Skills with this comprehensive guide based on Anthropic official documentation. Learn skill architecture, progressive disclosure patterns, bundled resources, and production-ready implementation strategies.

## Free Tools
- [Claude Code Skills Generator](http://websearchapi.ai/free-tools/claude-code-skills-generator): Generate professional Claude Code skills with AI
- [Search Domains by Technology](http://websearchapi.ai/free-tools/search-domains-by-technology): Find websites using specific technologies
- [Reverse Domain Company Lookup](http://websearchapi.ai/free-tools/reverse-domain-company-lookup): Find company data from a domain

## Company
- [Our Story](http://websearchapi.ai/story): About WebSearchAPI.ai
- [Contact](http://websearchapi.ai/contact): Get in touch
- [Careers](http://websearchapi.ai/careers): Join our team