원문에서 더 깊이 읽기
GEO·AI 검색·마케팅 관련 자료를 주제별로 찾아보세요.
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. > Claude Code Desktop opens your app in the iOS Simulator pane when Claude builds, runs, or checks it, with a separate simulator for each session. > [!NOTE] > > The iOS Simulator pane is in public beta in Claude Code Desktop on macOS. It's available on Pro, Max, Ultra, Team, and Enterprise plans, except in Enterprise organizations that have a HIPAA configuration enabled. The iOS Simulator pane shows your app running in Apple's iOS Simulato
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. > Set up scheduled tasks in Claude Code Desktop to run Claude automatically on a recurring basis for daily code reviews, dependency audits, or morning briefings. Scheduled tasks start a new session automatically at a time and frequency you choose. Use them for recurring work like daily code reviews, dependency update checks, or morning briefings that pull from your calendar and inbox. The Desktop app's **Scheduled tasks** page lists both l
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 Code sessions inside a WSL 2 distribution on Windows On Windows, the Code tab can run a session inside a WSL 2 distribution instead of on Windows itself. The session's Claude Code process, its tools, and git all execute inside the distribution, using its Linux toolchain and native Linux paths, the same environment your project targets. Use a WSL session when your repository lives inside the distribution's filesystem. Working on those
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. > Install and update the Claude desktop app on Ubuntu and Debian > [!NOTE] > > Linux support for the Claude desktop app is in beta. The desktop app on Linux gives you the same Chat, Cowork, and Claude Code experience as on macOS and Windows: parallel sessions, visual diff review, an integrated terminal and editor, and live app preview. See [Use Claude Code Desktop](https://code.claude.com/docs/en/desktop.md) for the feature reference. * A
Search Engine Journal · AI 검색 · 2026. 10. 31.
Google's spam guide adds indexing advice for pages made for sharing. Other updates cover restaurant ordering controls, report dates and AI Mode revenue. The post Spam Guide Update, Restaurant Controls & AI Mode Revenue – SEO Pulse appeared first on Search Engine Journal .
Search Engine Journal · 콘텐츠 · SEO · 2026. 10. 31.
Shopify's performance reviews asked how staff used AI. Its CEO says the answers didn't matter, and the question can give a company a reputation. The post Shopify CEO Says AI Performance Review Answers ‘Didn’t Matter’ appeared first on Search Engine Journal .
Search Engine Journal · AI 검색 · 2026. 10. 31.
New research identifies a potential weakness in big-brand visibility that smaller publishers may be able to exploit. The post Big Brands Dominate AI Search But Leave Openings For Smaller Sites appeared first on Search Engine Journal .
Search Engine Journal · AI 검색 · 2026. 10. 31.
Developers can apply to bring apps into AI Mode and the Gemini app, and Google's policy bars misleading descriptions meant to get an app picked. The post Google Opens Connected Apps Preview For AI Mode & Gemini appeared first on Search Engine Journal .
Perplexity · 공식 API 문서 · AI 검색 · 발행일 미상
> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Connect a remote MCP server to an Agent API request and optionally approve tool calls before they run. Beyond the `function` tools you define yourself, you can give a model new capabilities by connecting it to a remote [Model Context Protocol](https://modelcontextprotocol.io) (MCP) server. The model calls that server's tools to reach and control external services when it needs them to answer a prompt. The `mcp` tool connects a user-supplie
Perplexity · 공식 API 문서 · AI 검색 · 발행일 미상
> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Search for professionals, employees, and people using People Search in the Agent API The `people_search` tool enables models to find people and retrieve their professional information such as names, job titles, and companies. Use it to power workflows like lead research, recruiting pipelines, or organizational mapping. Use it when your application needs to: * Look up a specific person's professional background * Find employees at a company
Perplexity · 공식 API 문서 · AI 검색 · 발행일 미상
> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Retrieve structured financial and market data in the Agent API. `finance_search` lets the model pull structured financial and market data for public companies, ETFs, and related instruments. The model decides which fields to fetch based on your prompt. Use it when one answer needs more than one type of financial data, such as valuation, earnings, and context for the same company or list of companies. | Data area | What it includes | | - |
Perplexity · 공식 API 문서 · AI 검색 · 발행일 미상
> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Fetch and extract content from specific URLs in the Agent API. The `fetch_url` tool fetches and extracts content from specific URLs during an Agent API request. Use it when your application already knows which page, article, document, or report the model should inspect. Use `fetch_url` when you need full page content from known URLs. Use [`web_search`](https://docs.perplexity.ai/docs/agent-api/tools/web-search) when the model first needs t
Perplexity · 공식 API 문서 · AI 검색 · 발행일 미상
> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Execute code in isolated containers from inside an Agent API request. The `sandbox` tool lets the model run code during an Agent API request. The agent can execute code in an isolated container, inspect the output, and use the result in its final answer. You don't supply the code. You enable the tool, and the model writes and runs the code itself based on your prompt and instructions - then reads its own `stdout`/`stderr` back and uses it
Perplexity · 공식 API 문서 · AI 검색 · 발행일 미상
> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Search for web images from the Agent API with result limits, domain and format filters, typed results, streaming events, and per-invocation pricing. The `image_search` tool lets the model search for existing photographs, diagrams, illustrations, and other images on the web during an Agent API request. Results are returned as structured `image_search_results` output items, separate from the assistant's text. ```python Python theme={null} fr
Perplexity · 공식 API 문서 · AI 검색 · 발행일 미상
> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Search the web from the Agent API with filters, search configurations, pricing, parameters, and response fields. The `web_search` tool lets the model search the web during an Agent API request. Use it for current information, recent news, source-grounded research, and questions that need information beyond the model's training data. Enable the tool by adding it to the `tools` array. The model decides when to call it based on your prompt an
Perplexity · 공식 API 문서 · AI 검색 · 발행일 미상
> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > The tools an Agent API run can call - Perplexity-hosted built-in tools, remote MCP servers, and your own custom functions - and where to go for each. Tools are what turn a model into an agent. On its own a model answers only from what it already knows; tools let it search the live web, fetch a page, run code, or call into your own systems. You enable tools by listing them in the `tools` array, and within a single request the model runs an
Perplexity · 공식 블로그·기술 문서 · AI 검색 · 발행일 미상
Research Research Oct 21, 2026 A good teacher meets the student where they are A new self-distillation method that jointly trains teacher and student to improve model performance and training efficiency on complex reasoning and agentic tasks. Sep 23, 2026 Escaping SPACE: Part I Red-teaming VM isolation and network confinement for AI agents. Oct 12, 2026 Building shared workspaces for people and agents How Perplexity Projects keep long-running work persistent, concurrent, and traceable. Oct 7, 2026 Multimodal embeddings beyond a single vector A new family of late-interaction models for text and
Perplexity · 공식 API 문서 · AI 검색 · 발행일 미상
> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Specify multiple models in a fallback chain for higher availability and automatic failover. Model fallback enables specifying multiple models in a `models` array. The API tries each model in order until one succeeds, providing automatic failover when a model is unavailable. Provide a `models` array containing up to 5 models: 1. The API tries the first model in the array 2. If it fails or is unavailable, the next model is tried 3. This cont
Perplexity · 공식 API 문서 · AI 검색 · 발행일 미상
> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Run an Agent API request with a reusable, versioned configuration that you save and manage. A profile is a reusable, versioned configuration that you save and manage. It bundles the settings that shape a run, including the model or model fallback chain, system instructions, reasoning effort, tools, Skills, managed connectors, and the agent loop step budget, under a single ID. Select a profile by ID instead of repeating the full configurati
Google · Search Central 블로그 · 콘텐츠 · SEO · 발행일 미상
Home Search Central Google Search Central Blog Send feedback More ways to share your shipping and returns policies with Google Wednesday, November 12, 2025 Shipping speed, cost, and return policies are critical factors for online shoppers. When customers have clear information on fulfillment, it builds trust and improves their shopping experience. Last year, we launched shipping and return policies in Search Console for merchants with a configured Merchant Center account. We also enabled all merchants to add organization-level return policies with structured data for the first time. We're exci
Google · Search Central 블로그 · 리서치 · 발행일 미상
Home Search Central Google Search Central Blog Send feedback Adding context to your Search Console data with custom annotations Monday, November 17, 2025 We're always looking for new ways to help you understand your data and make smarter decisions when it comes to Google Search. That's why we're happy to announce a new feature within the Search Console performance reports: Custom annotations . This feature is designed to empower you to add your own contextual notes directly to your performance charts. Think of it as a personal notebook for your Search data. There are many ways to improve your
OpenAI · 공식 도움말 · 콘텐츠 · SEO · 발행일 미상
Why am I getting "Sorry, you have been blocked" Error? Resolve Cloudflare access blocks by checking your VPN, network location, or temporary IP restrictions. Updated: 11 days ago The "Sorry, you have been blocked" error can result from IP blocks by Cloudflare. These occur when suspicious activity is detected. If you're receiving this error, this may be due to: VPN usage : VPNs can sometimes trigger a block as they mask your original IP, which can be identified as suspicious. Geolocation : If your IP originates from a high-risk area, Cloudflare may block your access. You may regain access when
OpenAI · 공식 도움말 · 콘텐츠 · SEO · 발행일 미상
Why Am I Being Asked to Verify My Login? Understand login verification requests and troubleshoot one-time passwords or push-notification approvals. Updated: 8 days ago In some situations, you may be asked to complete an additional verification step when logging in — such as confirming a request from your mobile app or entering a code sent to your email. This helps ensure only you can access your account, especially on new or unrecognized devices. You may be required to verify your login if: You’re logging in from a new or unrecognized device There’s been an attempt to log in from an unusual lo
Google · Search Central 블로그 · 리서치 · 발행일 미상
Home Search Central Google Search Central Blog Send feedback Introducing the branded queries filter in Search Console Thursday, November 20, 2025 Following the Query groups launch last month, we're happy to announce we're providing an additional tool to analyze the performance of your website by query type in the Search Console Performance Report : the branded queries filter. This new feature is designed to help analyze the queries driving traffic to your site by automatically differentiating between branded and non-branded queries. What is a branded query? A branded query is a query that incl