526 pages for prompts.

go Claude Developer Platform · in the page cli-sdks-libraries/sdks/go …, message.Content) ``` </Accordion> <Accordion title="System prompts"> ```go message, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{ Model: anthropic.… typescript Claude Developer Platform · in the page cli-sdks-libraries/sdks/typescript …o Claude API types, reducing boilerplate when working with MCP tools, prompts, and resources. <Tip> The Claude API also supports an [`mcp_servers` parameter](https://platform.claude.com/docs/en/age… get-started Claude Developer Platform · in the page get-started …aude/working-with-messages"> Learn multi-turn conversations, system prompts, stop reasons, and other core patterns. </Card> Once you're comfortable with the basics, explore further: <CardGroup col… intro Claude Developer Platform · in the page intro …ur API key. Keep the key out of source control, client-side code, and prompts. Check whether your workload can use Workload Identity Federation instead of a static key. [Read the authentication g… access-transparency Claude Developer Platform · in the page manage-claude/access-transparency …----- | | Claude API (`api.anthropic.com`) | Yes | Prompts, completions, and data directly embedded in the API inputs | | Claude Code (using… api-and-data-retention Claude Developer Platform · in the page manage-claude/api-and-data-retention …t storage needs. Where a feature does not require storage of customer prompts or responses, it may be eligible for ZDR. Where a feature necessarily requires storage, Anthropic designs for the smallest… cmek Claude Developer Platform · in the page manage-claude/cmek …ed. * Portions of the Compliance API that return raw content, such as prompts, responses, and files, are disabled. * Structured outputs are not available for Claude Fable or Claude Mythos models in CM… compliance-api Claude Developer Platform · in the page manage-claude/compliance-api …xisting Compliance Access Key. OpenTelemetry logging can also capture prompts and responses, but Anthropic recommends the Compliance API for retrieving the content of Cowork and Claude Code sessions.… compliance-faq Claude Developer Platform · in the page manage-claude/compliance-faq …ata and a messages endpoint that returns the session transcript (user prompts, assistant responses, and tool calls and results). The local family adds a third endpoint that retrieves one session's met… compliance-integration-patterns Claude Developer Platform · in the page manage-claude/compliance-integration-patterns …er binary content, inside session transcripts (transcripts carry user prompts, assistant responses, and tool activity only; local session transcripts show a placeholder `text` block where binary conte… compliance-sessions Claude Developer Platform · in the page manage-claude/compliance-sessions …ngle conversation with Claude; its transcript is the sequence of user prompts, assistant responses, and tool calls and results in that conversation. The endpoints support eDiscovery (electronic discov… inference-hooks Claude Developer Platform · in the page manage-claude/inference-hooks …d from attachments. It never receives raw file or image bytes, system prompts, or Anthropic-internal context. The Inference hooks system doesn't keep its own copy of prompt or response content. It st… inference-hooks-configuration Claude Developer Platform · in the page manage-claude/inference-hooks-configuration …the Owner and Primary owner roles hold. </Note> Inference hooks send prompts from your organization to an AI security server you choose, and hold each request for an allow or deny verdict before Clau… inference-hooks-endpoint Claude Developer Platform · in the page manage-claude/inference-hooks-endpoint …extracted attachment text, and prior turns. It never includes system prompts, tool definitions, Anthropic-internal context, Claude's hidden reasoning, or raw file bytes. A turn whose every block is… First request Claude Developer Platform · in the page manage-claude/usage-cost-api …form.claude.com/docs/en/build-with-claude/prompt-caching) or specific prompts to make the most of your allocated capacity. * **Advanced analysis:** Perform deeper data analysis than what's available i… events-and-streaming Claude Developer Platform · in the page managed-agents/events-and-streaming …havior * **Track token usage:** Monitor token consumption to optimize prompts and reduce costs * **Use system prompts:** Add logging instructions to the system prompt so the agent summarizes what it d… memory Claude Developer Platform · in the page managed-agents/memory …ess by default. If the agent processes untrusted input (user-supplied prompts, fetched web content, or third-party tool output), a successful prompt injection could write malicious content into the st… multiagent-orchestration Claude Developer Platform · in the page managed-agents/multiagent-orchestration …lts. * **Specialization:** Route to agents with domain-focused system prompts and tools, such as a security agent or a documentation agent, rather than loading a single agent with every capability. *… Or, for the Project Glasswing model with the same capabilities: Claude Developer Platform · in the page models/fable-5-1/migration-guide …e-5-1-from-fable-5). * Re-evaluate `effort` (start at `high`), review prompts near the 512-token caching minimum, and re-baseline cost and latency. Per-token pricing differs. ## Migrating to Claude M… overview Claude Developer Platform · in the page models/fable-5-1/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/claude-fable-5-1"> The system prompt Claude Fable 5.1 uses on claude.ai and the Claude apps. </Card> <Card title=… introducing-claude-fable-5-and-claude-mythos-5 Claude Developer Platform · in the page models/fable-5/introducing-claude-fable-5-and-claude-mythos-5 …laude models, with a few differences in how to structure long-context prompts and reasoning instructions. See [Prompting Claude Fable 5](https://platform.claude.com/docs/en/build-with-claude/prompt-en… Or, for the model with the same capabilities and no access approval requirement: Claude Developer Platform · in the page models/fable-5/migration-guide …hos-5` is 512 tokens, lower than the 1,024 tokens on Claude Opus 4.8. Prompts that were too short to cache on Claude Opus 4.8 can now create cache entries, with no code changes required. See [Prompt c… overview Claude Developer Platform · in the page models/fable-5/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/overview#claude-fable-5"> The system prompt Claude Fable 5 uses on claude.ai and the Claude apps. </Card> <Card t… From Haiku 3.5 Claude Developer Platform · in the page models/haiku-4-5/migration-guide …e/strengthen-guardrails/handle-streaming-refusals). 4. **Update your prompts for behavioral changes** Claude 4 models have a more concise, direct communication style. Review [prompting best pract… overview Claude Developer Platform · in the page models/haiku-4-5/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/overview#claude-haiku-4-5"> The system prompt Claude Haiku 4.5 uses on claude.ai and the Claude apps. </Card> <Ca… overview Claude Developer Platform · in the page models/opus-4-5/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/overview#claude-opus-4-5"> The system prompt Claude Opus 4.5 uses on claude.ai and the Claude apps. </Card> <Card… overview Claude Developer Platform · in the page models/opus-4-6/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/overview#claude-opus-4-6"> The system prompt Claude Opus 4.6 uses on claude.ai and the Claude apps. </Card> <Card… overview Claude Developer Platform · in the page models/opus-4-7/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/overview#claude-opus-4-7"> The system prompt Claude Opus 4.7 uses on claude.ai and the Claude apps. </Card> <Card… overview Claude Developer Platform · in the page models/opus-4-8/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/overview#claude-opus-4-8"> The system prompt Claude Opus 4.8 uses on claude.ai and the Claude apps. </Card> <Card… migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …om to think and act; start at 64k tokens and tune from there. If your prompts were tuned for running without thinking, see [Prompts written for thinking disabled](https://platform.claude.com/docs/en/b… overview Claude Developer Platform · in the page models/opus-5-5/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/claude-opus-5-5"> The system prompt Claude Opus 5.5 uses on claude.ai and the Claude apps. </Card> <Card title="S… whats-new-opus-5-5 Claude Developer Platform · in the page models/opus-5-5/whats-new-opus-5-5 …. If your Claude Opus 5 integration ran with thinking disabled, see [Prompts written for thinking disabled](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-o… overview Claude Developer Platform · in the page models/opus-5/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/overview#claude-opus-5"> The system prompt Claude Opus 5 uses on claude.ai and the Claude apps. </Card> <Card tit… Models overview Claude Developer Platform · in the page models/overview …-like interactions. If you prefer more concise responses, adjust your prompts to guide the model toward the desired output length. Refer to the [prompt engineering guides](https://platform.claude.com/… overview Claude Developer Platform · in the page models/sonnet-4-5/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/overview#claude-sonnet-4-5"> The system prompt Claude Sonnet 4.5 uses on claude.ai and the Claude apps. </Card> <… overview Claude Developer Platform · in the page models/sonnet-4-6/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/overview#claude-sonnet-4-6"> The system prompt Claude Sonnet 4.6 uses on claude.ai and the Claude apps. </Card> <… migration-guide Claude Developer Platform · in the page models/sonnet-5-5/migration-guide …ficient-tools-2025-02-19` and `output-128k-2025-02-19`. * Review your prompts. ### Claude Haiku 4.5 only * Replace [`claude-haiku-4-5-20251001`](https://platform.claude.com/docs/en/models/sonnet-5-5… overview Claude Developer Platform · in the page models/sonnet-5-5/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/claude-sonnet-5-5"> The system prompt Claude Sonnet 5.5 uses on claude.ai and the Claude apps. </Card> <Card titl… overview Claude Developer Platform · in the page models/sonnet-5/overview …"text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/claude-sonnet-5"> The system prompt Claude Sonnet 5 uses on claude.ai and the Claude apps. </Card> <Card title="S… overview Claude Developer Platform · in the page release-notes/overview …Console is being sunset with access ending on August 17, 2026. Saved prompts, variables, and evals are not supported in the updated [Workbench](https://platform.claude.com/playground). You can export… handle-streaming-refusals Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/handle-streaming-refusals …s:** Monitor refusal frequency to identify potential issues with your prompts ## Migration notes If you built refusal handling when this feature first shipped, or you're adding it to an existing int… increase-consistency Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/increase-consistency …ues during setup.</answer> </response> ``` </Accordion> ## Chain prompts for complex tasks Break down complex tasks into smaller, consistent subtasks. Each subtask gets Claude's full attention,… mitigate-jailbreaks Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks …jailbreaks and prompt injection with input screening, hardened system prompts, and safe handling of untrusted tool content. --- Jailbreaking and prompt injection are attempts to make Claude ignore it… reduce-hallucinations Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/reduce-hallucinations …*Iterative refinement**: Use Claude's outputs as inputs for follow-up prompts, asking it to verify or expand on previous statements. This can catch and correct inconsistencies. * **External knowledge… reduce-latency Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/reduce-latency …r the response will be. Here are some tips to help you optimize your prompts and outputs: * **Be clear but concise:** Aim to convey your intent clearly and concisely in the prompt. Avoid unnecessary… reduce-prompt-leak Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/reduce-prompt-leak …g context from user queries, filtering Claude's outputs, and auditing prompts, without degrading task performance. --- Prompt leaks can expose sensitive information that you expect to be "hidden" in… Use Claude Code with a screen reader Claude Code CLI · in the page accessibility …laude's replies and thinking, tool activity, errors and warnings, and prompts. The labels are also searchable, so you can jump between sections of the transcript by searching your terminal's scrollbac… Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …cloud provider plans, Anthropic doesn't train models on your code or prompts. Your API provider determines retention and compliance posture. | Topic | What to know | Where to start | | :- | :- | :-… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …n, which is fine for well-scoped tasks but can run long on open-ended prompts ("improve this codebase"). Setting a budget is a good default for production agents. See [Turns and budget](#turns-and-bud… Use Claude Code features in the SDK Claude Code CLI · in the page agent-sdk/claude-code-features …via `systemPrompt` without using CLAUDE.md files. See [Modify system prompts](/docs/en/agent-sdk/modifying-system-prompts). Use CLAUDE.md when you want the same context shared between interactive Cla…