Anthropic · Claude 공식 문서 · AI 마케팅 · 발행일 미상
--- title: Manage tool context url: https://platform.claude.com/docs/en/agents-and-tools/tool-use/manage-tool-context description: Choose among tool search, programmatic tool calling, prompt caching, and context editing to manage context bloat. --- Tool definitions and accumulated `tool_result` blocks consume your context window. Long-running agents with many tools or many turns can exhaust available context before the task is complete. Four approaches address this at different points in the pipeline. Each approach targets a different source of context pressure. Pick the one that matches where
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. > Add an MCP server to Claude Code, verify the connection, and find the configuration on disk. The [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) lets Claude Code use tools beyond its built-in set, such as searching an issue tracker, querying a database, or controlling a web browser. These tools come from MCP servers, which run on your machine or as hosted services. This guide walks you through connecting one
Anthropic · Claude 공식 문서 · AI 마케팅 · 발행일 미상
--- title: How tool use works url: https://platform.claude.com/docs/en/agents-and-tools/tool-use/how-tool-use-works description: Understand the tool use loop, where tools run, and when to use tools instead of prose. --- This page explains the concepts behind tool use: where tools run, how the agentic loop works, and when tool use is the right approach. For hands-on guidance, start with the [Build a tool-using agent](https://platform.claude.com/docs/en/agents-and-tools/tool-use/build-a-tool-using-agent) tutorial or the [Define tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use
Anthropic · Claude Code 문서 · AI 마케팅 · 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. > Isolate parallel Claude Code sessions in separate git worktrees so changes don't collide. Covers the `--worktree` flag, subagent isolation, `.worktreeinclude`, cleanup, and non-git VCS hooks. A [git worktree](https://git-scm.com/docs/git-worktree) is a separate working directory with its own files and branch, sharing the same repository history and remote as your main checkout. Running each Claude Code session in its own worktree gives i
Anthropic · Claude 공식 문서 · AI 마케팅 · 발행일 미상
--- title: Handle tool calls url: https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls description: Parse tool_use blocks, format tool_result responses, and handle errors with is_error. --- This page covers the tool-call lifecycle: reading `tool_use` blocks from Claude’s response, formatting `tool_result` blocks in your reply, and signaling errors. For the SDK abstraction that handles this automatically, see [Tool Runner](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner). **Simpler with Tool Runner:** The manual tool handling described on thi
Anthropic · Claude Code 문서 · 리서치 · 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. > Dynamic workflows orchestrate many subagents from a script Claude writes and you can rerun. Use them for codebase audits, large migrations, and cross-checked research. > [!NOTE] > > Dynamic workflows are available on all paid plans, with Anthropic API access, and on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. On Pro, turn them on from the Dynamic workflows row in `/config`. A dynamic workflow is a JavaScript scr
Anthropic · Claude 공식 문서 · 콘텐츠 · SEO · 발행일 미상
--- title: Handle streaming refusals url: https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/handle-streaming-refusals description: Detect and handle refusal stop reasons in streaming responses, and retry refused requests on a fallback model. featureMetadata: 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-sonnet-5 - claude-haiku-5-5 - claude-haiku-4-5-20251001 - claude-opus-4-8 - claude-opus-4-7 - claude-opus-4-6 - claude-sonnet-4-6 - claud
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. > Let Claude list and message your other Claude Code sessions on this machine, and reach your sessions on other machines or in the cloud. > [!NOTE] > > Cross-session messaging requires Claude Code v2.1.224 or later on macOS and Linux, including Linux inside WSL 2. On native Windows, it requires Claude Code v2.1.234 or later. When a session meets the requirements, messaging is on with nothing to enable. See [Availability](#availability) for
Anthropic · Claude 공식 문서 · 콘텐츠 · SEO · 발행일 미상
--- title: Get your Claude API key url: https://platform.claude.com/docs/en/get-api-key description: Find, create, and manage your API keys for the Claude API in the Claude Console. --- API keys for the Claude API (also called Anthropic API keys) live in the Claude Console. To view your existing keys or create a new one, go to the [API keys](https://platform.claude.com/settings/keys) page (`platform.claude.com/settings/keys`) in the Console. When you create a key, you choose its type, which determines what the key can do, where it works, and when it stops working. A **personal key** acts as yo
Anthropic · Claude Code 문서 · AI 마케팅 · 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. > Coordinate multiple Claude Code instances working together as a team, with shared tasks, inter-agent messaging, and centralized management. > [!WARNING] > > Agent teams are experimental and disabled by default. Enable them by setting `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` in your [settings.json](https://code.claude.com/docs/en/settings.md) or environment. Without that variable, no team is set up at session start, no team directories ar
Anthropic · Claude 공식 문서 · AI 마케팅 · 발행일 미상
--- title: Fine-grained tool streaming url: https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming description: Stream tool inputs without server-side JSON buffering for latency-sensitive applications. featureMetadata: status: stable zdr: eligibility: eligible note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements). 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 - cla
Anthropic · Claude Code 문서 · AI 마케팅 · 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. > Dispatch and manage many Claude Code sessions from one screen. Agent view shows what every session is doing and which ones need your input. Agent view, opened with `claude agents`, is one screen for all your background sessions: what's running, what needs your input, and what's done. Dispatch new sessions, watch their state at a glance instead of scrolling through transcripts, and step in only when one needs you. Each background session
Search Engine Journal · 콘텐츠 · SEO · 2026. 11. 1.
A shared robots.txt line could let sites opt out of AI training with several providers at once, but companies involved are handling it differently. The post Google, Microsoft & OpenAI Plan To Honor Shared AI Training Opt-Out 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. > Register Perplexity's Search API as a tool inside the Anthropic Messages API and run the standard tool-use loop with Claude. This guide shows how to expose Perplexity's [Search API](https://docs.perplexity.ai/docs/search/quickstart.md) to Claude as a tool. The Anthropic Messages API uses a manual tool-use loop: the model emits a `tool_use` block, you execute the tool (in this case, call `client.search.create`), and you send the result back
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. > An agents-first Python SDK that brings Perplexity's Search as Code approach to your applications: composable retrieval primitives that agents orchestrate in code. Traditional search treats retrieval as a monolith: a model issues a query, the search engine runs a predefined pipeline, and the model consumes the processed results. That contract breaks down for agents working on complex, open-ended tasks — it produces coarse context, wastes th
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. > Learn best practices for optimizing search queries and implementing efficient async patterns with Perplexity's Search API. This guide covers essential best practices for getting the most out of Perplexity's Search API, including query optimization techniques and efficient async usage patterns for high-performance applications. **1. Write specific queries** Use highly specific queries for more targeted results. For example, instead of searc
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. > Use search_type fast on the Search API for lower-latency, lower-cost web results. Fast Search reduces search latency and cost in agent workflows. Set `search_type: "fast"` on a Search API request, or on the `perplexity_search` tool in the [Perplexity MCP server](#use-fast-search-in-the-mcp-server). The Search API charges \$1.00 per 1,000 Fast Search requests instead of \$5.00 for standard web search. > [!NOTE] > > For Fast Search inside th
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. > Access real-time web search results with Perplexity's Search API. Get ranked results, domain filtering, multi-query search, and content extraction for developers. Perplexity's Search API returns real-time, ranked web results as structured data, with controls for domains, languages, regions, and extracted content. Use the Search API when you need raw results for your own processing. For an LLM-generated answer with citations, use the [Agent
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 Search API returns ranked web results as JSON, not a generated answer. What each result contains, the request controls and limits, the price per request, and when to use it instead of the Agent API. The Search API is one endpoint, `POST https://api.perplexity.ai/search`. You send a query and get back ranked web results as structured data for your own code to filter, store, or hand to a model. There is no generated answer and no token b
OpenAI · 공식 도움말 · AI 검색 · 발행일 미상
Verifying your domain for OpenAI identity Learn how to verify a company or school domain, review where it applies, and avoid sign-in conflicts. Updated: 10 days ago Overview Domain verification confirms that your company or institution controls an email domain. A verified domain can support your tenant’s identity settings and single sign-on (SSO). Verifying a domain does not by itself enable SSO, configure System for Cross-domain Identity Management (SCIM), or grant product access. If automatic account creation is on for a ChatGPT workspace mapped to the domain, eligible people can join that w
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. > How to write effective prompts for the Agent API. The Agent API runs a bounded multi-turn loop: on each turn the model can call a tool (such as `web_search`), read the result, and decide whether to continue or answer. Prompts that work well with single-shot LLMs often underperform here, because the same text shapes tool selection, search query generation, and final response together. Two parameters drive most of the prompt design: * **`ins
OpenAI · 공식 도움말 · AI 검색 · 발행일 미상
Verifying Communications from OpenAI Identify official OpenAI websites, social media accounts, apps, email domains, and phone numbers. Updated: 4 days ago OpenAI uses social media to communicate company news, announcements, and updates. We share information and communicate using our accounts below. Platform Handle Website https://openai.com Blog https://openai.com/news Service status https://status.openai.com Support help.openai.com Facebook @OpenAI Instagram @openai @chatgpt @soraofficial @ChatGPTindia LinkedIn OpenAI ChatGPT ChatGPT for Education OpenAI for Business OpenAI Global Affairs Tik
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. > How Agent API effort levels perform against Sonar across the benchmarks we run, and which effort level to use in place of each Sonar model. On the benchmarks we run, Agent API effort levels deliver more quality per dollar than Sonar: the effort level curve sits above every Sonar model. The lead is widest on hard, multi-step browsing: on BrowseComp, the strongest effort level scores nearly three times the best Sonar model. We evaluated Agen
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. > Move a Sonar chat completions integration to the Agent API, including requests, responses, search, effort levels, async runs, and parameter mappings. This guide maps a Sonar chat completions integration to the Agent API. You keep the same grounded web search, and gain an agent that runs multi-step research, executes its own code, and calls tools like finance and people search. The fastest path is to let your coding agent do the migration.