1,063 pages for prompt.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.
choosing-an-environment
Claude Developer Platform · in the page
managed-agents/choosing-an-environment
…agent definition is the same whichever you choose. You set the model, prompt, and tools on the [agent](https://platform.claude.com/docs/en/managed-agents/agent-setup), not on the environment. ## Star…
environments
Claude Developer Platform · in the page
managed-agents/environments
…files, fetched web content, or third-party tool output), a successful prompt injection could use an allowed host to copy files out of the sandbox. To reduce this risk, set the `bash` tool’s [permissio…
events-and-streaming
Claude Developer Platform · in the page
managed-agents/events-and-streaming
…t as a `role: "system"` turn. It doesn’t replace the top-level system prompt, which the `system` (csharp, go: `System`; ruby: `system_`) field on the agent definition sets. <CodeGroup> ```bash cURL…
memory
Claude Developer Platform · in the page
managed-agents/memory
…and a note describing each mount is automatically added to the system prompt, telling the agent where to look. The [agent toolset](https://platform.claude.com/docs/en/managed-agents/tools) is required…
migration
Claude Developer Platform · in the page
managed-agents/migration
…dle" end ``` </CodeGroup> ### What you still control * **System prompt and model:** Same fields, now on the agent definition. * **Custom tools:** Still declared with JSON Schema. Execution moves…
multiagent-orchestration
Claude Developer Platform · in the page
managed-agents/multiagent-orchestration
…when to use them. To guide that choice, tell the agent in its system prompt when to use a workflow run. See [Tell the agent when to use a run](https://platform.claude.com/docs/en/managed-agents/multi…
onboarding
Claude Developer Platform · in the page
managed-agents/onboarding
…you through each field of an agent definition: * **Model and system prompt:** Pick a model and write the system prompt in a full-width editor. * **MCP servers:** Add remote MCP servers by URL and au…
overview
Claude Developer Platform · in the page
managed-agents/overview
…----------------------------------- | | **What it is** | Direct model prompting access | Pre-built, configurable agent harness that runs in managed infrastructure | | **Best for** | Cu…
quickstart
Claude Developer Platform · in the page
managed-agents/quickstart
…----------------------------- | | **Agent** | The model, system prompt, tools, MCP servers, and skills | | **Environment** |…
secure-deployment
Claude Developer Platform · in the page
managed-agents/secure-deployment
…edential) for the request in every language. Keep keys out of system prompts, agent definitions, and messages. Do not give the agent a Claude API key or Claude API access token. Even when one is in a…
secure-deployment-monitoring
Claude Developer Platform · in the page
managed-agents/secure-deployment-monitoring
…review flags behavior beyond what the agent was granted. For a review prompt, setup steps, and working code, see the [security review recipe](https://platform.claude.com/cookbook/managed-agents-cma-ag…
secure-deployment-risks
Claude Developer Platform · in the page
managed-agents/secure-deployment-risks
…s in content that an agent reads can steer the agent. This is called [prompt injection](https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks). Claude is inhe…
spawn.sh: called once per claimed work item
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes
…If you use a different working directory, update your agent's system prompt so Claude can locate the skill files. * **Outputs:** on self-hosted environments the session's system prompt omits the `/mn…
self-hosted-sandboxes-memory
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-memory
…nder `/mnt/memory/` that cloud sessions use, and the session’s system prompt describes it to the agent. For example, a store named “User Preferences” lands at `/mnt/memory/user-preferences/`. 2. **Ope…
self-hosted-sandboxes-reference
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-reference
…If you use a different working directory, update your agent’s system prompt so Claude can locate the skill files. | |…
session-observability
Claude Developer Platform · in the page
managed-agents/session-observability
…| | `cache_read_input_tokens` | Tokens read from the prompt cache.…
session-threads
Claude Developer Platform · in the page
managed-agents/session-threads
…hread_status_terminated` events. * **Message events:** A run thread’s prompt, an `agent.thread_message_received` event, stays on its own stream. * **Run events:** `workflow_run.*` events also arrive o…
sessions
Claude Developer Platform · in the page
managed-agents/sessions
…ample starts a session that overrides the model and clears the system prompt: <CodeGroup> ```bash cURL curl -fsSL https://api.anthropic.com/v1/sessions \ -H "x-api-key: $ANTHROPIC_API_KEY" \…
vaults
Claude Developer Platform · in the page
managed-agents/vaults
…he grant is gone or the OAuth server rejected the refresh with a 4xx. Prompt the end user to re-authorize. * `unknown`: a transient error (5xx, 429, or network failure). Wait and retry. <CodeGroup>…
workflow-runs
Claude Developer Platform · in the page
managed-agents/workflow-runs
…s://platform.claude.com/docs/en/managed-agents/session-threads), on a prompt that the program wrote. An agent in a run can be an inline agent, which the program defines itself, or a [predefined agent]…
Or, for Claude Mythos 5.1, which offers the same capabilities to verified organizations:
Claude Developer Platform · in the page
models/fable-5-1/migration-guide
…r contact your Anthropic account team. For behavioral differences and prompting patterns, see [Prompting Claude Fable 5.1](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prom…
overview
Claude Developer Platform · in the page
models/fable-5-1/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
whats-new-fable-5-1
Claude Developer Platform · in the page
models/fable-5-1/whats-new-fable-5-1
…To make the model call a tool rather than reply in text, state in the prompt when the tool applies (for example, “Use the `get_weather` tool to answer”). Claude Fable 5.1 follows explicit tool instruc…
overview
Claude Developer Platform · in the page
models/fable-5/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
overview
Claude Developer Platform · in the page
models/haiku-4-5/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
migration-guide
Claude Developer Platform · in the page
models/haiku-5-5/migration-guide
…5/migration-guide#use-the-claude-haiku-5-5-model-id). 2. Recount your prompts, and revisit `max_tokens` limits and cost estimates, because the same text counts as more tokens and large images count as…
overview
Claude Developer Platform · in the page
models/haiku-5-5/overview
…](https://platform.claude.com/docs/en/models/haiku-5-5/overview). For prompting guidance, see [Prompting Claude Haiku 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prom…
whats-new-haiku-5-5
Claude Developer Platform · in the page
models/haiku-5-5/whats-new-haiku-5-5
…](https://platform.claude.com/docs/en/models/haiku-5-5/overview). For prompting guidance, see [Prompting Claude Haiku 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prom…
overview
Claude Developer Platform · in the page
models/mythos-5-1/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
overview
Claude Developer Platform · in the page
models/mythos-5/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
overview
Claude Developer Platform · in the page
models/opus-4-5/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
overview
Claude Developer Platform · in the page
models/opus-4-6/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
overview
Claude Developer Platform · in the page
models/opus-4-7/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
overview
Claude Developer Platform · in the page
models/opus-4-8/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
migration-guide
Claude Developer Platform · in the page
models/opus-5-5/migration-guide
…s-5-5#feature-support). For behavioral differences and model-specific prompting patterns, see [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/promp…
overview
Claude Developer Platform · in the page
models/opus-5-5/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
whats-new-opus-5-5
Claude Developer Platform · in the page
models/opus-5-5/whats-new-opus-5-5
…. To make the model call a tool rather than reply in text, say in the prompt when the tool applies. The migration guide shows the [before and after for tool choice](https://platform.claude.com/docs/en…
overview
Claude Developer Platform · in the page
models/opus-5/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
Models overview
Claude Developer Platform · in the page
models/overview
…latency:** Relative to the current lineup. Actual latency depends on prompt length, output length, and thinking effort. * **Pricing:** Base price per million tokens. Batch API requests are 50% off; p…
overview
Claude Developer Platform · in the page
models/sonnet-4-5/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
overview
Claude Developer Platform · in the page
models/sonnet-4-6/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
migration-guide
Claude Developer Platform · in the page
models/sonnet-5-5/migration-guide
…Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, except for prompt cache reads, which cost $0.10 USD per million tokens, half the Claude Sonnet 5 rate. See [Claude pricing](https://platform.…
overview
Claude Developer Platform · in the page
models/sonnet-5-5/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
whats-new-sonnet-5-5
Claude Developer Platform · in the page
models/sonnet-5-5/whats-new-sonnet-5-5
…. To make the model call a tool rather than reply in text, say in the prompt when the tool applies. The migration guide shows the [before and after](https://platform.claude.com/docs/en/models/sonnet-5…
overview
Claude Developer Platform · in the page
models/sonnet-5/overview
…utput, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and C…
overview
Claude Developer Platform · in the page
release-notes/overview
…ws": {"type": "enabled"}}`. To guide the agent, tell it in its system prompt when to start a run. Follow each run through `workflow_run.*` events on the session’s event stream. See [Workflow runs](htt…
develop-tests
Claude Developer Platform · in the page
test-and-evaluate/develop-tests
…uations to measure performance against them. This cycle is central to prompt engineering. <Frame> ![Flowchart of prompt engineering: test cases, preliminary prompt, iterative testing and refinement…
handle-streaming-refusals
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
…build-with-claude/fallback-credit) token so the retry doesn’t pay the prompt-cache cost twice. Claude Haiku 5.5 refusals carry no fallback credit. * **Provide custom messaging:** Create user-friendly…
increase-consistency
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/increase-consistency
…aude.com/docs/en/build-with-claude/structured-outputs) instead of the prompt engineering techniques below. Structured outputs provide guaranteed schema compliance and are specifically designed for thi…
mitigate-jailbreaks
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks
--- title: Mitigate jailbreaks and prompt injections url: https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks description: Defend your application against j…