950 pages for agent.

Retrieve remote session messages Claude Developer Platform · in the page api/compliance/apps/sessions/remote/messages/list …null` Identifier of the human account that sent this turn on an agent-owned session. Null on user-owned sessions, where every user-role turn was sent by the session's `user`. - `next_page: stri… Organizations Claude Developer Platform · in the page api/compliance/organizations …The member's "Global instructions" text for Cowork, Claude's desktop agent, with leading and trailing whitespace removed. `null` when the member has never set it or has cleared it. - `user: object… User Preferences Claude Developer Platform · in the page api/compliance/organizations/user_preferences …The member's "Global instructions" text for Cowork, Claude's desktop agent, with leading and trailing whitespace removed. `null` when the member has never set it or has cleared it. - `user: object… List organization members' personal preferences Claude Developer Platform · in the page api/compliance/organizations/user_preferences/list …The member's "Global instructions" text for Cowork, Claude's desktop agent, with leading and trailing whitespace removed. `null` when the member has never set it or has cleared it. - `user: object… errors Claude Developer Platform · in the page api/errors …Use `auto` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) to keep tool inputs schema-valid, or [structured outputs](https://platform.claude.com/d… Messages Claude Developer Platform · in the page api/messages …tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterpris… Batches Claude Developer Platform · in the page api/messages/batches …- `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and e… Create a Message Batch Claude Developer Platform · in the page api/messages/batches/create …- `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and e… Retrieve Message Batch results Claude Developer Platform · in the page api/messages/batches/results …- `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discover… Count tokens in a Message Claude Developer Platform · in the page api/messages/count_tokens …tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterpris… Create a Message Claude Developer Platform · in the page api/messages/create …tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterpris… spans Claude Developer Platform · in the page api/opentelemetry/spans …s://platform.claude.com/docs/en/api/beta/sessions/events#beta_managed_agents_user_interrupt_event) event. A stream's span ends when the stream ends. If the application closes the stream early, the SD… overview Claude Developer Platform · in the page api/overview …that provides programmatic access to Claude models and Claude Managed Agents. <Note> **New to Claude?** For direct model access, start with [Get started](https://platform.claude.com/docs/en/get-sta… rate-limits Claude Developer Platform · in the page api/rate-limits …age/limits) page in the Claude Console. </Tab> </Tabs> ### Managed Agents [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) endpoints are rate-limited for each o… Message Batches API Claude Developer Platform · in the page build-with-claude/batch-processing …use, including all [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools) (web search, web fetch, code execution, MCP connectors, advisor, and tool search) * System… claude-in-amazon-bedrock Claude Developer Platform · in the page build-with-claude/claude-in-amazon-bedrock …ude model? The [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model) in Claude Code applies model ID swaps and breaki… claude-in-microsoft-foundry Claude Developer Platform · in the page build-with-claude/claude-in-microsoft-foundry …ude in Microsoft Foundry * Admin API * Advisor tool * Claude Managed Agents * Compliance API * Models API * Message Batches API * Server-side fallback (the [`fallbacks` parameter](https://platform.cl… claude-on-amazon-bedrock-legacy Claude Developer Platform · in the page build-with-claude/claude-on-amazon-bedrock-legacy …ith-claude/thinking) * [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), including the [Bash tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-… claude-on-vertex-ai Claude Developer Platform · in the page build-with-claude/claude-on-vertex-ai …ude Models on Google Cloud (Google managed) as part of Google Cloud's Agent Platform. You can call Claude with Anthropic's client SDKs. --- [Claude Models on Google Cloud](https://platform.claude.com… claude-platform-on-aws Claude Developer Platform · in the page build-with-claude/claude-platform-on-aws …u the full Anthropic platform experience, including the Messages API, Agent Skills, code execution, and beta features, accessible through your AWS account. Unlike [Amazon Bedrock](https://platform.cla… sent_count = len(messages sent in the compaction request) Claude Developer Platform · in the page build-with-claude/compaction …ended strategy for managing context in long-running conversations and agentic workflows. It handles context management automatically, without client-side summarization code. </Tip> Compaction extends… compaction-on-demand Claude Developer Platform · in the page build-with-claude/compaction-on-demand …next turn. The SDK [tool runner](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner) in Python, TypeScript, C#, Go, Java, PHP, and Ruby can send the compaction request for you.… compaction-threshold Claude Developer Platform · in the page build-with-claude/compaction-threshold …://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents). </Tip> This is ideal for: * Chat-based, multi-turn conversations where you want users to use one chat for a long period… context-editing Claude Developer Platform · in the page build-with-claude/context-editing …://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents). This page covers: * **Tool result clearing:** Best for agentic workflows with heavy tool use where old tool results are… context-windows Claude Developer Platform · in the page build-with-claude/context-windows …ly approach context window limits. For long-running conversations and agentic workflows, [server-side compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) is the primary strat… effort Claude Developer Platform · in the page build-with-claude/effort …| Long-running agentic and coding tasks (over 30 minutes) with token budgets in the millions | | `high` | Spends as many tokens as the task nee… This will automatically use the environment variable VOYAGE_API_KEY. Claude Developer Platform · in the page build-with-claude/embeddings …1024 (default), 256, 512, 2048 | Optimized for **code** retrieval and agentic coding applications. See the [voyage-code-4 blog post](https://blog.voyageai.com/2026/08/13/voyage-code-4/) for details.… extended-thinking Claude Developer Platform · in the page build-with-claude/extended-thinking …ls used through the Messages API](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). How platforms treat the beta header differs. The Claude API and [Claude Platform on AWS](htt… fast-mode Claude Developer Platform · in the page build-with-claude/fast-mode …aude API: availability: ga note: Includes [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview). Microsoft Foundry: availability: ga note: Av… files Claude Developer Platform · in the page build-with-claude/files …n using the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) to provide inputs (for example, datasets and documents) and then download outputs (… handling-stop-reasons Claude Developer Platform · in the page build-with-claude/handling-stop-reasons …mentations, use the [tool runner](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner), which automatically handles tool execution, result formatting, and conversation management… mid-conversation-effort-example Claude Developer Platform · in the page build-with-claude/mid-conversation-effort-example …ion: Build a session-level mode that grants standing consent for multiagent fan-out, switched on and off with mid-conversation system messages. --- An orchestration mode is a session-level switch: wh… mid-conversation-system-messages Claude Developer Platform · in the page build-with-claude/mid-conversation-system-messages …tools` array, and [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector) tools can be referenced individually with `mcp_tool_reference` (`server_name` and `name`) or as a… multilingual-support Claude Developer Platform · in the page build-with-claude/multilingual-support …ltilingual output quality. </Card> <Card title="Customer support agent" icon="headset" href="https://platform.claude.com/docs/en/about-claude/use-case-guides/customer-support-chat"> Build a l… overview Claude Developer Platform · in the page build-with-claude/overview …-------------- | | [Advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) | Pair a faster executor model with a higher-intelligence advisor model that prov… pdf-support Claude Developer Platform · in the page build-with-claude/pdf-support …at high volume. * [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview): To extract specific information from documents for use as tool inputs. </Step> </Steps> ##… preserved-thinking Claude Developer Platform · in the page build-with-claude/preserved-thinking …ng Nothing changes for you if Claude Code, claude.ai, Claude Managed Agents, or the Claude Agent SDK builds your requests, or if your code keeps `system` and `tools` fixed for a session and only ever… Request 2 caches its request content (not the response) Claude Developer Platform · in the page build-with-claude/prompt-caching …ilor your prompt caching strategy to your scenario: * Conversational agents: Reduce cost and latency for extended conversations, especially those with long instructions or uploaded documents. * Codin… claude-prompting-best-practices Claude Developer Platform · in the page build-with-claude/prompt-engineering/claude-prompting-best-practices …st models, covering clarity, examples, XML structuring, thinking, and agentic systems. --- This is the reference for prompt engineering with current Claude models, including Claude Fable 5.1, Claude… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …gnificantly more dependable at dispatching and sustaining parallel subagents, and reliably manages ongoing communication with long-running subagents and peer agents. Beyond these specific improvement… Delivering work Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5-1 …h triggering, safeguard false positives, file edits, long outputs, subagents, and vision. --- For the model's capabilities, API changes, pricing, and availability, see [What's new in Claude Fable 5.1… prompting-claude-haiku-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-haiku-5-5 …ompting-claude-haiku-5-5#json-output-with-your-own-tools) * In a long agent prompt, the model stops before the work is done and hands the task back: [Prevent early stopping in long agent prompts](http… prompting-claude-opus-4-8 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-4-8 …Claude Opus 4.8, covering verbosity, effort calibration, tool use, subagents, and frontend defaults. --- This guide covers the prompting patterns specific to Claude Opus 4.8. For the API changes invo… prompting-claude-opus-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5 …nd prompting patterns for Claude Opus 5, covering response verbosity, agentic narration, task scoping, subagent delegation, self-correction, and output artifacts when thinking is disabled. --- This g… prompting-claude-opus-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5-5 …r in API integrations and chat, progress updates, unattended and multiagent tasks, safeguard refusals, frontend design, complex visual inputs, multiapp workflows, and pasted text in user messages." --… prompting-claude-sonnet-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5 …t-practices). Claude Sonnet 5 has particular strengths in coding and agentic tasks. It performs well out of the box on existing Claude Sonnet 4.6 prompts. The patterns in this guide cover the behavio… prompting-claude-sonnet-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 …/prompting-claude-sonnet-5-5#reasoning-tasks-with-json-output) * Long agentic turns look silent: [User-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering… refusals-and-fallback Claude Developer Platform · in the page build-with-claude/refusals-and-fallback …session.** A single turn can produce several refusals, for example an agent plus its subagents. * **Configure fallback on every request path.** Retry handlers, error-recovery branches, and background… search-results Claude Developer Platform · in the page build-with-claude/search-results …he tool call with [`tool_choice`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools#forcing-tool-use), so the retrieval step runs every time. ### Example: Knowledge base tool… skills-guide Claude Developer Platform · in the page build-with-claude/skills-guide --- title: Using Agent Skills with the API url: https://platform.claude.com/docs/en/build-with-claude/skills-guide description: Learn how to use Agent Skills to extend Claude's capabilities through th…