원문에서 더 깊이 읽기
GEO·AI 검색·마케팅 관련 자료를 주제별로 찾아보세요.
Google · Search Central 문서 · 콘텐츠 · SEO · 발행일 미상
Home Search Central Documentation Send feedback Fix Search-related JavaScript problems This guide helps you identify and fix JavaScript issues that may be blocking your page, or specific content on JavaScript powered pages, from showing up in Google Search. While Google Search does run JavaScript, there are some differences and limitations that you need to account for when designing your pages and applications to accommodate how crawlers access and render your content. Our guide on JavaScript SEO basics has more information on how you can optimize your JavaScript site for Google Search. Google
Google · Lighthouse · 콘텐츠 · SEO · 발행일 미상
Home Docs Lighthouse Best Practices audits Detected JavaScript libraries Stay organized with collections Save and categorize content based on your preferences. Lighthouse lists all front-end JavaScript libraries detected on the page: This is a diagnostic audit This audit simply lists all the front-end JavaScript libraries your page uses. Resources Source code for Detected JavaScript libraries audit
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback Combine built-in tools and function calling Gemini allows the combination of built-in tools , such as google_search , and function calling (also known as custom tools ) in a single interaction by preserving and exposing the context history of tool calls. Built-in and custom tool combinations allow for complex, agentic workflows where, for example, the model can ground itself in real-time web data before calling your specific business logic. Here's an example that enables built-in and custom tool combinations with
Google · Search Central 문서 · 콘텐츠 · SEO · 발행일 미상
Home Search Central Documentation Send feedback Remove your AMP pages from Google Search This page describes how web developers can remove their AMP pages from Google Search. There are three options for removing AMP content: Quickly remove all versions of a page , including the AMP and canonical non-AMP pages Remove only the AMP page that is paired with a canonical non-AMP page, while keeping the canonical non-AMP page live Remove AMP content with a CMS (with options to remove all versions of a page, or only the AMP version) Remove all versions of AMP content, including AMP and non-AMP This se
Google · Lighthouse · 콘텐츠 · SEO · 발행일 미상
Home Docs Lighthouse Best Practices audits Uses deprecated APIs Stay organized with collections Save and categorize content based on your preferences. Deprecated APIs are scheduled to be removed from Chrome. Calling these APIs after they're removed causes errors on your site. How the Lighthouse deprecated API audit fails Lighthouse flags pages that call deprecated APIs: Lighthouse includes all deprecated API warnings that Chrome logs to the DevTools Console. How to remove deprecated APIs Go to Chrome Platform Status and expand the entries for the APIs that you're using to learn why the APIs ar
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback File search The Gemini API enables Retrieval Augmented Generation ("RAG") through the File Search tool. File Search imports, chunks, and indexes your data to enable fast retrieval of relevant information based on a provided prompt. This retrieved information is then used as context for the model, allowing it to provide more accurate and relevant answers. File search is also able to provide multimodal capabilities with text embeddings supported by gemini-embedding-001 , and image/multimodal embedding supported by g
Google · Search Central 문서 · 리서치 · 발행일 미상
Home Search Central Documentation Send feedback Validate your AMP content After you've created AMP content , here are some ways to validate your AMP content: Use the AMP Test Tool to ensure that your AMP content is valid. For applicable AMP content types , use the Rich Results Test to verify that your structured data parses properly. Use the AMP status report to monitor the performance of all AMP pages on your site. Fix common AMP errors If your AMP page doesn't appear in Google Search, try the following steps: Make your page discoverable by linking your pages. Did you add rel="amphtml" to the
Google · Lighthouse · 콘텐츠 · SEO · 발행일 미상
Home Docs Lighthouse Best Practices audits Uses Application Cache Stay organized with collections Save and categorize content based on your preferences. The Application Cache, also known as AppCache, is deprecated . How the Lighthouse Application Cache audit fails Lighthouse flags pages that use the Application Cache: This audit fails when Lighthouse finds a reference to the Application Cache manifest in a page's tag. For example, this markup causes the audit to fail: ... Use the Cache API instead of the Application Cache To pass this audit, remove the manifest from your page, and use the Cach
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback Computer use The Computer Use tool lets you build browser, mobile, and desktop control agents that interact with and automate tasks. Using screenshots, the model can "see" a computer screen, and "act" by generating specific UI actions like mouse clicks and keyboard inputs. Similar to function calling, you will need to implement the client-side execution environment to receive and execute the Computer Use actions. For the list of supported models, see Model versions . Gemini 4 and Gemini 3.x models support several
Google · Lighthouse · 콘텐츠 · SEO · 발행일 미상
Home Docs Lighthouse Best Practices audits Prevents users from pasting into input fields Stay organized with collections Save and categorize content based on your preferences. Some websites claim that allowing users to paste passwords reduces security. However, password pasting actually improves security because it enables the use of password managers. Password managers typically generate strong passwords for users, store them securely, and then automatically paste them into password fields whenever users need to log in. This approach is generally more secure than forcing users to type in pass
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback URL context The URL context tool lets you provide additional context to the models in the form of URLs. By including URLs in your request, the model will access the content from those pages (as long as it's not a URL type listed in the limitations section ) to inform and enhance its response. The URL context tool is useful for tasks like the following: Extract Data : Pull specific info like prices, names, or key findings from multiple URLs. Compare Documents : Analyze multiple reports, articles, or PDFs to identif
Google · Lighthouse · GEO · AEO · 발행일 미상
Home Docs Lighthouse Best Practices audits Requests the geolocation permission on page load Stay organized with collections Save and categorize content based on your preferences. Users are mistrustful of or confused by pages that automatically request their location on page load. How the Lighthouse geolocation audit fails Lighthouse flags pages that request geolocation permission on load: Lighthouse audit showing geolocation request on page load. Lighthouse checks all JavaScript executed on page load. If the script calls geolocation.getCurrentPosition() or geolocation.watchPosition() , and geo
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback Code execution The Gemini API provides a code execution tool that enables the model to generate and run Python code. The model can then learn iteratively from the code execution results until it arrives at a final output. You can use code execution to build applications that benefit from code-based reasoning. For example, you can use code execution to solve equations or process text. You can also use the libraries included in the code execution environment to perform more specialized tasks. Gemini is only able to
Google · AI 기술 블로그 · 리서치 · 발행일 미상
Sep 15, 2026 Share x.com Facebook LinkedIn Mail Copy link AI for Societal Impact For over a decade, we’ve seen artificial intelligence steadily advance scientific discovery, shifting from theoretical research to real-world impact. Today, the potential of these tools is no longer hypothetical — it is measurable and fundamentally reshaping how we solve humanity's most complex challenges. Across the globe, we’re partnering with communities and researchers who are putting AI to work in key areas that matter most: making disease detectable, treatable, and preventable, predicting natural disasters,
Google · Lighthouse · 콘텐츠 · SEO · 발행일 미상
Home Docs Lighthouse Best Practices audits Requests the notification permission on page load Stay organized with collections Save and categorize content based on your preferences. Good notifications are timely, relevant, and precise . If your page asks for permission to send notifications on page load, those notifications may not be relevant to your users or their needs. How the Lighthouse notification audit fails Lighthouse flags pages that request notification permissions on load: Lighthouse checks all JavaScript executed on page load. If the code calls notification.requestPermission() , and
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback Grounding with Google Maps Grounding with Google Maps connects the generative capabilities of Gemini with the rich, factual, and up-to-date data of Google Maps. This feature enables developers to easily incorporate location-aware functionality into their applications. When a user query has a context related to Maps data, the Gemini model leverages Google Maps to provide factually accurate and fresh answers that are relevant to the user's specified location or general area. Accurate, location-aware responses: Lever
Google · Lighthouse · 리서치 · 발행일 미상
Home Docs Lighthouse Best Practices audits Mitigate DOM-based XSS with Trusted Types Stay organized with collections Save and categorize content based on your preferences. Trusted Types are a web platform security feature that helps prevent certain DOM-based XSS attacks , by blocking risky injection points (like .innerHTML ) from using unvalidated string values. If a risky injection point is blocked, a violation is raised. The Content-Security-Policy (CSP) header utilizes the require-trusted-types-for directive to enforce Trusted Types. How the Lighthouse audit fails Lighthouse report warning
Anthropic · Claude 공식 문서 · 리서치 · 발행일 미상
--- title: MCP tunnels security url: https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/security description: Hardening guidance, credential rotation, breach response, and teardown for MCP tunnel deployments. --- MCP tunnels are in research preview. [Request access](https://claude.com/form/mcp-tunnels) to try them. The tunnel architecture provides strong defaults (outbound-only connectivity, end-to-end encryption, and IP validation), but the overall security of your [tunnel stack](https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/concepts#components) also depends o
Anthropic · Claude 공식 문서 · 리서치 · 발행일 미상
--- title: MCP tunnels reference url: https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/reference description: Proxy configuration fields, the Tunnels REST API, certificate requirements, and the setup component. --- MCP tunnels are in research preview. [Request access](https://claude.com/form/mcp-tunnels) to try them. The [proxy](https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/concepts#components) reads its configuration from `/etc/mcp-gateway/config.yaml` (Compose) or the rendered ConfigMap (Helm, populated from `gateway.config.*`). | Field | Description | Defa
Anthropic · Claude Code 문서 · 콘텐츠 · SEO · 발행일 미상
> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt > Use this file to discover all available pages before exploring further. > Run shell commands automatically when Claude Code edits files, finishes tasks, or needs input. Format code, send notifications, validate commands, and enforce project rules. Hooks are user-defined shell commands. Claude Code runs them at specific points in its lifecycle, which gives you deterministic control: certain actions always happen rather than relying on the LLM to choose to run them. Use hooks to enforce project rules, automate r
Anthropic · Claude 공식 문서 · AI 마케팅 · 발행일 미상
--- title: MCP connector url: https://platform.claude.com/docs/en/agents-and-tools/mcp-connector description: Connect to remote MCP servers directly from the Messages API without an MCP client, and allowlist, denylist, or configure individual tools. featureMetadata: status: beta betaHeader: mcp-client-2026-09-15, mcp-client-2025-11-20 zdr: eligibility: not-eligible note: Data retained according to standard policy. supportedModels: - claude-fable-5-1 - claude-mythos-5-1 - claude-fable-5 - claude-mythos-5 - claude-mythos-preview - claude-opus-5-5 - claude-opus-5 - claude-sonnet-5-5 - claude-sonn
Anthropic · Claude Code 문서 · 콘텐츠 · SEO · 발행일 미상
📊 Summary Files {stats["files"]:,} Directories {stats["dirs"]:,} Total size {fmt(data["size"])} File types {len(stats["extensions"])} By file type {lang_bars} 📁 {escape(data["name"])}
Anthropic · Claude 공식 문서 · 리서치 · 발행일 미상
--- title: Manage tunnels in the Claude Console url: https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/console description: Create tunnels, register CA certificates, retrieve the tunnel token, and attach tunneled MCP servers to agents from the Claude Console. --- MCP tunnels are in research preview. [Request access](https://claude.com/form/mcp-tunnels) to try them. This page covers the Console side of an MCP tunnels deployment: creating a tunnel, registering your CA certificate, retrieving the tunnel token, and attaching the [upstream MCP servers](https://platform.claude.com/doc
Anthropic · Claude Code 문서 · 콘텐츠 · SEO · 발행일 미상
> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt > Use this file to discover all available pages before exploring further. > Learn how to connect Claude Code to your tools with the Model Context Protocol. Claude Code can connect to hundreds of external tools and data sources through the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction), an open source standard for AI-tool integrations. MCP servers give Claude Code access to your tools, databases, and APIs. Connect a server when you find yourself copying data into chat from another to