{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-07-28T06:20:51.496Z","headline":"Anthropic 发布\"Claude 食谱\"教程合集","description":"Anthropic 发布\"Claude 食谱\"合集，包含多个教程，覆盖从复现 Claude 智能体搜索基准分数到构建异步多智能体团队、部署生产级智能体等场景。教程还涉及 Memory 存储、Outcomes 自验证循环及从 OpenAI Agents SDK 迁移等实操内容。","url":"https://www.aioga.com/news/cmrywwsva05zhrolgzua9cma2/","mainEntityOfPage":"https://www.aioga.com/news/cmrywwsva05zhrolgzua9cma2/","datePublished":"2026-07-24T11:55:45.881Z","dateModified":"2026-07-24T11:55:45.881Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://platform.claude.com/cookbook","https://aihot.virxact.com/items/cmrywwsva05zhrolgzua9cma2"],"canonicalUrl":"https://www.aioga.com/news/cmrywwsva05zhrolgzua9cma2/","directAnswer":{"@type":"Answer","text":"Aioga 编辑摘要：Anthropic 发布\"Claude 食谱\"合集，包含多个教程，覆盖从复现 Claude 智能体搜索基准分数到构建异步多智能体团队、部署生产级智能体等场景。 Aioga 将其归入「技巧观点」方向，重点关注它对真实使用和行业竞争的影响。","url":"https://www.aioga.com/news/cmrywwsva05zhrolgzua9cma2/","dateCreated":"2026-07-24T11:55:45.881Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"platform.claude.com source article","url":"https://platform.claude.com/cookbook","datePublished":"2026-07-24T11:55:45.881Z","provider":{"@type":"Organization","name":"platform.claude.com","url":"https://platform.claude.com/cookbook"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmrywwsva05zhrolgzua9cma2","datePublished":"2026-07-24T11:55:45.881Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmrywwsva05zhrolgzua9cma2"}}],"aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","originalPublisher":{"name":"platform.claude.com","url":"https://platform.claude.com/cookbook"},"article":{"id":"cmrywwsva05zhrolgzua9cma2","slug":"cmrywwsva05zhrolgzua9cma2","url":"https://www.aioga.com/news/cmrywwsva05zhrolgzua9cma2/","title":"Anthropic 发布\"Claude 食谱\"教程合集","title_en":"《克劳德食谱》","summary":"Anthropic 发布\"Claude 食谱\"合集，包含多个教程，覆盖从复现 Claude 智能体搜索基准分数到构建异步多智能体团队、部署生产级智能体等场景。教程还涉及 Memory 存储、Outcomes 自验证循环及从 OpenAI Agents SDK 迁移等实操内容。","source":"Hacker News 热门（buzzing.cc 中文翻译）","sourceUrl":"https://platform.claude.com/cookbook","aiHotUrl":"https://aihot.virxact.com/items/cmrywwsva05zhrolgzua9cma2","publishedAt":"2026-07-24T11:55:45.881Z","category":"技巧观点","score":44,"selected":false,"articleBody":["Build a Messages API harness that reproduces published DeepSearchQA and BrowseComp scores, using programmatic tool calling, server-side compaction, and task budgets.","Detect safety classifier blocks on Fable 5 and fall back to Opus 4.8 with server-side or SDK-based client-side fallback, including streaming behavior and the new billing changes.","Two async multi-agent patterns — a fixed N-agent team with peer messaging through a shared hub, and dynamically spawned async subagents — reduced to their bare messaging and lifecycle mechanics.","Deploy the research agent from notebook 00 through three tiers of operational maturity (Docker, Modal, Kubernetes) with the same container image and HTTP interface at every tier.","Heterogeneous team via the multiagent coordinator config — a coordinator runs three specialists (web-search researcher, file-reading librarian, rules-based pricer) with scoped toolsets to assemble a sales proposal. Covers the multiagent field, the thread_created / thread_message_received event types, and per-role tool scoping.","Build a grade-and-revise loop with Outcomes: a writer drafts a cited research brief, a stateless grader fetches every URL and checks every quote against a rubric, and feedback drives revisions until the brief passes. Covers user.define_outcome, the span.outcome_evaluation_* events, and how to write a rubric the grader can act on.","Give your Claude Managed Agents a Memory store so they learn and remember your users' preferences across multiple interactions.","Build a vulnerability-discovery agent with the Claude Agent SDK that threat-models a C target, hunts memory-safety bugs with built-in file tools, and triages findings into a structured report.","Wire Claude into your on-call flow: when an alert fires, the agent reads logs and runbooks, pinpoints the root cause, opens a fix PR, and waits for your approval before merging.","Build an analyst that turns a CSV into a narrative HTML report with interactive charts, using a sandboxed environment and file mounting.","Mention the bot with a CSV to get an analysis report in-thread, with multi-turn follow-ups on the same session.","Entry-point tutorial for the Claude Managed Agents API. Walks through agent / environment / session creation, file mounts, and the streaming event loop by getting an agent to fix three planted bugs in a calc.py package.","End-to-end production story for Managed Agents — vault-backed MCP credentials, the session.status_idled webhook pattern for human-in-the-loop without long-lived connections, and the resource lifecycle CRUD verbs.","Server-side prompt versioning — create v1, evaluate against a labelled test set, ship v2, detect a regression, roll back by pinning sessions to version 1. Covers agents.update, version pinning on sessions.create, and where the review gate moves when prompts are not code.","Build an agent that autonomously investigates IOCs by querying multiple threat intel sources, cross-referencing findings, mapping to MITRE ATT&CK, and producing structured reports for SIEM and SOAR integration.","List, read, rename, tag, and fork Agent SDK sessions on disk to build a conversation history sidebar without writing a transcript parser.","Build knowledge graphs from unstructured text using Claude for entity extraction, relation mining, deduplication, and multi-hop graph querying.","Compare context engineering strategies for long-running agents and learn when each applies, what it costs, and how they compose.","Port an OpenAI Agents SDK app to the Claude Agent SDK, mapping each primitive (tools, guardrails, sessions, handoffs) through a single expense-approval agent example.","Build an incident response agent with read-write MCP tools for autonomous diagnosis, remediation, and post-mortem documentation.","Manage long-running Claude conversations with instant session memory compaction using background threading and prompt caching.","Reduce latency and token consumption by letting Claude write code that calls tools programmatically in the code execution environment.","Scale Claude applications to thousands of tools using semantic embeddings for dynamic tool discovery.","Manage context limits in long-running agentic workflows by automatically compressing conversation history.","Build a low-latency voice assistant using ElevenLabs for speech-to-text and text-to-speech combined with Claude.","Give Claude a crop tool to zoom into image regions for detailed analysis of charts, documents, and diagrams.","Guide to prompting Claude for distinctive, polished frontend designs avoiding generic aesthetics.","Build financial dashboards and portfolio analytics using Claude's Excel, PowerPoint, PDF skills.","Create, deploy, and manage custom skills extending Claude with specialized organizational workflows.","Create documents, analyze data, automate workflows with Claude's Excel, PowerPoint, PDF skills.","Build a research agent using Claude Code SDK with WebSearch for autonomous research.","Build multi-agent systems with subagents, hooks, output styles, and plan mode features.","Connect agents to external systems via MCP servers for GitHub monitoring and CI workflows.","Run parallel agent evaluations on tools independently from evaluation task files.","Programmatically access and analyze your Claude API usage and cost data via Admin API.","Build AI agents with persistent memory using Claude's memory tool and context editing.","Reduce time-to-first-token by warming cache speculatively while users formulate their queries.","Enable parallel tool calls on Claude 3.7 Sonnet using batch tool meta-pattern workaround.","Use Claude's extended thinking for transparent step-by-step reasoning with budget management.","Combine extended thinking with tools for transparent reasoning during multi-step workflows.","Three simple multi-LLM workflow patterns trading cost or latency for improved performance.","Workflow pattern using one LLM for generation and another for evaluation feedback loop.","Central LLM dynamically delegates tasks to worker LLMs and synthesizes their combined results.","Process large volumes of Claude requests asynchronously with 50% cost reduction using batches.","Convert natural language queries to SQL using RAG, chain-of-thought, and self-improvement techniques.","Improve RAG accuracy by adding context to chunks before embedding with prompt caching.","Step-by-step guide to finetuning Claude 3 Haiku on Amazon Bedrock for custom tasks.","Generate synthetic test cases to evaluate and improve your Claude prompt templates effectively.","Cache and reuse prompt context for cost savings and faster responses with detailed instructions.","Comprehensive guide to summarizing legal documents with evaluation and advanced techniques.","Build and optimize RAG systems with Claude using summary indexing and reranking techniques.","Build classification systems with Claude using RAG and chain-of-thought for insurance tickets.","Control how Claude selects tools using tool_choice parameter for forced or auto selection.","Combine Claude's vision with tools to extract structured data from images like nutrition labels.","Generate longer responses beyond max_tokens limit using prefill technique with message continuation.","Tips and techniques for optimal image processing performance with Claude's vision capabilities.","Create validated tools using Pydantic models for type-safe Claude tool use interactions.","Transcribe audio with Deepgram and generate interview questions using Claude for preparation.","Integrate Wolfram Alpha LLM API as Claude tool for computational queries and answers.","Provide Claude with calculator tool for arithmetic operations and mathematical problem solving."],"articleImages":[{"sourceUrl":"https://avatars.githubusercontent.com/u/44481408?v=4","alt":"Alexander Bricken","afterParagraph":1,"url":"/media/articles/cmrywwsva05zhrolgzua9cma2/742185d79f1ae89b.jpg"},{"sourceUrl":"https://avatars.githubusercontent.com/u/5667029?v=4","alt":"Mahesh Murag","afterParagraph":1,"url":"/media/articles/cmrywwsva05zhrolgzua9cma2/5bc9316485eb6b30.jpg"},{"sourceUrl":"https://avatars.githubusercontent.com/u/100530254?v=4","alt":"Kevin Tang","afterParagraph":3,"url":"/media/articles/cmrywwsva05zhrolgzua9cma2/ed9d9d01eacdcb91.jpg"}],"mediaStatus":"ok","articleBodyZh":["构建一个 Messages API 验证工具，通过编程方式调用工具、服务器端压缩和任务预算，重现已发布的 DeepSearchQA 和 BrowseComp 得分。","检测 Fable 5 上的安全分类器阻止，并回退到 Opus 4.8，支持服务器端或 SDK 基于客户端的回退，包括流式行为和新的计费变更。","两种异步多代理模式——固定 N 代理团队通过共享中心进行同伴消息传递，以及动态生成的异步子代理——简化为基本的消息和生命周期机制。","将笔记本 00 中的研究代理部署通过三个操作成熟度层级（Docker、Modal、Kubernetes），在每个层级使用相同的容器镜像和 HTTP 接口。","通过多代理协调器配置形成异构团队——一个协调器运行三个专家（网络搜索研究员、文件阅读图书管理员、基于规则的定价员），使用范围限定的工具集来组装销售提案。涵盖多代理领域、thread_created / thread_message_received 事件类型以及按角色的工具范围限定。","建立评分与修订循环与结果：作家起草带引用的研究简报，无状态评分员获取每个 URL 并根据评分标准检查每个引用，反馈驱动修订直至简报通过。涵盖 user.define_outcome、span.outcome_evaluation_* 事件，以及如何编写评分员可执行的评分标准。","为你的 Claude 托管代理提供一个 Memory 存储，以便它们在多次交互中学习并记住用户的偏好。","使用 Claude Agent SDK 构建漏洞发现代理，对 C 语言目标进行威胁建模，利用内置文件工具猎取内存安全漏洞，并将发现分级整理成结构化报告。","将 Claude 连接到你的值班流程：当警报触发时，代理读取日志和运行手册，定位根本原因，创建修复 PR，并在合并前等待你的批准。","构建一个分析员，将 CSV 转换为带交互图表的叙述 HTML 报告，使用沙箱环境和文件挂载。","提及该机器人并附上 CSV，即可在线程中获得分析报告，并在同一会话中进行多轮跟进。","Claude 管理代理 API 的入门教程。通过让一个代理修复 calc.py 包中三个预先植入的错误，演示代理/环境/会话创建、文件挂载以及流事件循环。","Managed Agents 的端到端生产案例 —— 使用保险库支持的 MCP 凭证、用于人机协作的 session.status_idled webhook 模式（无需长时间连接）以及资源生命周期的 CRUD 操作。","服务器端提示版本管理 —— 创建 v1，对照标记测试集进行评估，发布 v2，检测回归，通过将会话固定到版本 1 回滚。涵盖 agents.update、sessions.create 的版本固定，以及当提示不是代码时审查门的移动位置。","构建一个能够自主调查 IOC 的代理，通过查询多个威胁情报来源、交叉引用发现、映射到 MITRE ATT&CK，并生成用于 SIEM 和 SOAR 集成的结构化报告。","列出、读取、重命名、标记和分叉磁盘上的 Agent SDK 会话，以在无需编写转录解析器的情况下构建对话历史侧边栏。","使用 Claude 从非结构化文本构建知识图谱，用于实体提取、关系挖掘、去重和多跳图查询。","比较长期运行代理的上下文工程策略，并学习每种策略的适用场景、成本及其组合方式。","将 OpenAI Agents SDK 应用移植到 Claude Agent SDK，通过单个费用审批代理示例映射每个原语（工具、保护措施、会话、交接）。","构建一个使用读写 MCP 工具的事故响应代理，实现自主诊断、修复和事后文档记录。","通过后台线程和提示缓存，实现即时会话记忆压缩，管理长期运行的 Claude 对话。","通过让 Claude 编写代码在代码执行环境中以编程方式调用工具，降低延迟和 token 消耗。","使用语义嵌入实现动态工具发现，将 Claude 应用扩展到成千上万的工具。","在长期运行的代理工作流中，通过自动压缩对话历史管理上下文限制。","结合 ElevenLabs 的语音转文本和文本转语音功能，以及 Claude，构建低延迟语音助手。","为Claude提供裁剪工具，以便放大图像区域，详细分析图表、文档和图示。","引导提示Claude生成独特、精致的前端设计，避免通用美学。","使用Claude的Excel、PowerPoint和PDF技能构建财务仪表盘和投资组合分析。","创建、部署并管理自定义技能，通过专业的组织工作流程扩展Claude功能。","使用Claude的Excel、PowerPoint和PDF技能创建文档、分析数据、自动化工作流程。","使用Claude Code SDK和WebSearch构建研究代理，实现自主研究。","构建多代理系统，包含子代理、钩子、输出风格和计划模式功能。","通过MCP服务器将代理连接到外部系统，用于GitHub监控和CI工作流程。","独立于评估任务文件对工具进行并行代理评估。","通过Admin API以编程方式访问和分析Claude API使用情况及费用数据。","使用Claude的记忆工具和上下文编辑功能构建具有持久记忆的AI代理。","在用户制定查询时，通过投机性预热缓存以减少首次标记的时间。","使用批量工具元模式变通方法，在Claude 3.7 Sonnet上启用并行工具调用。","使用Claude的扩展思维进行透明的逐步推理，并进行预算管理。","在多步工作流程中，将扩展思维与工具结合以实现透明推理。","三种简单的多LLM工作流程模式，以成本或延迟换取性能提升。","工作流程模式：使用一个LLM生成内容，另一个LLM提供评估反馈循环。","中央LLM动态分配任务给工作LLM，并综合它们的结果。","使用批处理异步处理大量Claude请求，成本降低50%。","使用RAG、链式思维和自我改进技术，将自然语言查询转换为SQL。","通过在嵌入前向块添加上下文并使用提示缓存，提高RAG准确性。","逐步指南：在Amazon Bedrock上微调Claude 3 Haiku以完成自定义任务。","生成合成测试案例，以有效评估和改进您的Claude提示模板。","缓存并重用提示上下文，通过详细说明节省成本并加快响应速度。","全面指南，概述法律文件的总结方法，包括评估和高级技术。","使用Claude构建和优化RAG系统，通过摘要索引和重新排序技术提高性能。","使用RAG和思维链在Claude中构建保险票据分类系统。","使用tool_choice参数控制Claude选择工具的方式，可实现强制或自动选择。","结合Claude的视觉功能和工具，从图像中提取结构化数据，如营养标签。","使用预填充技术和消息续传生成超出max_tokens限制的更长响应。","关于使用Claude视觉功能实现最佳图像处理性能的技巧和方法。","使用Pydantic模型创建经过验证的工具，实现类型安全的Claude工具使用交互。","使用Deepgram转录音频，并使用Claude生成面试问题作为准备。","将Wolfram Alpha LLM API集成为Claude工具，用于计算查询和答案。","为Claude提供计算器工具，用于算术运算和数学问题解决。"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"Aioga 编辑摘要：Anthropic 发布\"Claude 食谱\"合集，包含多个教程，覆盖从复现 Claude 智能体搜索基准分数到构建异步多智能体团队、部署生产级智能体等场景。 Aioga 将其归入「技巧观点」方向，重点关注它对真实使用和行业竞争的影响。","background":"背景分析：实践类内容的价值在于是否能被复现、是否有明确边界，以及它能否转化为稳定的开发或工作流方法。","viewpoint":"Aioga 判断：这条动态更适合作为行业观察信号，当前信息足以建立线索，但不足以推导长期结论。","implications":"影响分析：对相关团队而言，短期应先核对来源、可用范围和实际成本，再判断是否值得接入或跟进。","nextStep":"后续观察：继续观察示例是否可复现、工具版本变化、社区反馈和实际成本。","evidenceRefs":["title","summary","articleBody"],"confidence":"medium","status":"published","aiGenerated":false,"autoApproved":true,"generatedBy":"rule-safe-fallback","generatedAt":"2026-07-28T06:29:10.547Z","sourceHash":"d9f57719f6a9ef5e","validation":{"passed":true,"mode":"rule-safe-fallback","checks":["schema","length","source-attribution","no-html"]}},"tags":["技巧观点","Hacker News 热门（buzzing.cc 中文翻译）"],"translations":{"zh-CN":{"title":"Anthropic 发布\"Claude 食谱\"教程合集","summary":"Anthropic 发布\"Claude 食谱\"合集，包含多个教程，覆盖从复现 Claude 智能体搜索基准分数到构建异步多智能体团队、部署生产级智能体等场景。教程还涉及 Memory 存储、Outcomes 自验证循环及从 OpenAI Agents SDK 迁移等实操内容。","category":"技巧观点","source":"platform.claude.com","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic 发布\"Claude 食谱\"教程合集 - Aioga AI资讯","description":"Anthropic 发布\"Claude 食谱\"合集，包含多个教程，覆盖从复现 Claude 智能体搜索基准分数到构建异步多智能体团队、部署生产级智能体等场景。教程还涉及 Memory 存储、Outcomes 自验证循环及从 OpenAI Agents SDK 迁移等实操内容。","url":"https://www.aioga.com/news/cmrywwsva05zhrolgzua9cma2/"},"en":{"title":"Anthropic releases 'Claude Recipes' tutorial collection","summary":"Anthropic released the \"Claude Recipes\" collection, which includes multiple tutorials covering scenarios from reproducing Claude agent benchmark scores to building asynchronous multi-agent teams and deploying production-grade agents. The tutorials also involve practical content such as Memory storage, Outcomes self-verification loops, and migration from the OpenAI Agents SDK.","category":"Insights","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic releases 'Claude Recipes' tutorial collection - Aioga AI News","description":"Anthropic released the \"Claude Recipes\" collection, which includes multiple tutorials covering scenarios from reproducing Claude agent benchmark scores to building asynchronous mul...","url":"https://www.aioga.com/en/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:23:39.937Z"},"ja":{"title":"Anthropicが「Claudeレシピ」チュートリアル集を公開","summary":"Anthropic は「Claude レシピ」コレクションを公開しました。複数のチュートリアルが含まれており、Claude エージェントのベンチマークスコアの再現から、非同期マルチエージェントチームの構築、実運用レベルのエージェントのデプロイまでのシナリオをカバーしています。チュートリアルには、Memory ストレージ、Outcomes 自己検証ループ、OpenAI Agents SDK からの移行などの実践的な内容も含まれています。","category":"ヒントと視点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropicが「Claudeレシピ」チュートリアル集を公開 - Aioga AIニュース","description":"Anthropic は「Claude レシピ」コレクションを公開しました。複数のチュートリアルが含まれており、Claude エージェントのベンチマークスコアの再現から、非同期マルチエージェントチームの構築、実運用レベルのエージェントのデプロイまでのシナリオをカバーしています。チュートリアルには、Memory ストレージ、Outcomes 自己検証ループ、Op...","url":"https://www.aioga.com/ja/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:23:48.278Z"},"ko":{"title":"Anthropic에서 발표한 'Claude 레시피' 튜토리얼 모음","summary":"Anthropic가 'Claude 레시피' 컬렉션을 발표했으며, 여러 튜토리얼을 포함하고 있습니다. 튜토리얼은 Claude 에이전트의 벤치마크 점수 재현부터 비동기 다중 에이전트 팀 구성, 생산 수준 에이전트 배포 등 다양한 시나리오를 다룹니다. 또한 튜토리얼에는 메모리 저장, Outcomes 자체 검증 루프, OpenAI Agents SDK에서의 마이그레이션 등 실습 내용도 포함되어 있습니다.","category":"인사이트","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic에서 발표한 'Claude 레시피' 튜토리얼 모음 - Aioga AI 뉴스","description":"Anthropic가 'Claude 레시피' 컬렉션을 발표했으며, 여러 튜토리얼을 포함하고 있습니다. 튜토리얼은 Claude 에이전트의 벤치마크 점수 재현부터 비동기 다중 에이전트 팀 구성, 생산 수준 에이전트 배포 등 다양한 시나리오를 다룹니다. 또한 튜토리얼에는 메모리 저장, Outcomes 자체 검증 루프, OpenA...","url":"https://www.aioga.com/ko/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:24:46.073Z"},"es":{"title":"Anthropic publica la colección de tutoriales \"Recetas de Claude\"","summary":"Anthropic lanzó la colección \"Recetas de Claude\", que incluye varios tutoriales, abarcando desde la reproducción de las puntuaciones de referencia de búsqueda del agente Claude hasta la construcción de equipos asincrónicos de múltiples agentes, el despliegue de agentes de nivel de producción y otros escenarios. Los tutoriales también cubren contenido práctico como el almacenamiento de Memory, el ciclo de auto-verificación de Outcomes y la migración desde OpenAI Agents SDK.","category":"Ideas","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic publica la colección de tutoriales \"Recetas de Claude\" - Aioga Noticias de IA","description":"Anthropic lanzó la colección \"Recetas de Claude\", que incluye varios tutoriales, abarcando desde la reproducción de las puntuaciones de referencia de búsqueda del agente Claude has...","url":"https://www.aioga.com/es/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:24:32.092Z"},"fr":{"title":"Anthropic publie la collection de tutoriels \"Recettes Claude\"","summary":"Anthropic publie la collection de 'recettes Claude', comprenant plusieurs tutoriels, couvrant des scénarios allant de la reproduction des scores de référence de recherche de l'agent Claude à la construction d'équipes multi-agents asynchrones, et au déploiement d'agents de niveau production. Les tutoriels abordent également le stockage Memory, le cycle d'auto-validation Outcomes et la migration depuis le SDK OpenAI Agents.","category":"Analyses","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic publie la collection de tutoriels \"Recettes Claude\" - Aioga Actualités IA","description":"Anthropic publie la collection de 'recettes Claude', comprenant plusieurs tutoriels, couvrant des scénarios allant de la reproduction des scores de référence de recherche de l'agen...","url":"https://www.aioga.com/fr/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:25:30.423Z"},"de":{"title":"Anthropic veröffentlicht die 'Claude-Rezepte'-Tutorialsammlung","summary":"Anthropic veröffentlicht die \"Claude-Rezeptsammlung\", die mehrere Tutorials enthält und Szenarien abdeckt, von der Reproduktion der Benchmark-Ergebnisse des Claude-Agenten bis hin zum Aufbau asynchroner Multi-Agenten-Teams und der Bereitstellung produktionsreifer Agenten. Die Tutorials behandeln außerdem praktische Inhalte wie Memory-Speicherung, Outcomes-Selbstüberprüfungsschleifen und die Migration vom OpenAI Agents SDK.","category":"技巧观点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic veröffentlicht die 'Claude-Rezepte'-Tutorialsammlung - Aioga KI-News","description":"Anthropic veröffentlicht die \"Claude-Rezeptsammlung\", die mehrere Tutorials enthält und Szenarien abdeckt, von der Reproduktion der Benchmark-Ergebnisse des Claude-Agenten bis hin...","url":"https://www.aioga.com/de/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:25:42.618Z"},"pt-BR":{"title":"Anthropic lança coleção de tutoriais \"Claude Recipes\"","summary":"Anthropic lançou a coleção de \"receitas Claude\", que inclui vários tutoriais, cobrindo desde a reprodução das pontuações de referência de busca do agente inteligente Claude até a construção de equipes assíncronas de múltiplos agentes, implantação de agentes em nível de produção, entre outros cenários. Os tutoriais também abordam conteúdos práticos como armazenamento de Memory, ciclo de auto-verificação de Outcomes e migração do OpenAI Agents SDK.","category":"技巧观点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic lança coleção de tutoriais \"Claude Recipes\" - Aioga Notícias de IA","description":"Anthropic lançou a coleção de \"receitas Claude\", que inclui vários tutoriais, cobrindo desde a reprodução das pontuações de referência de busca do agente inteligente Claude até a c...","url":"https://www.aioga.com/pt-BR/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:26:23.333Z"},"ru":{"title":"Anthropic выпустила сборник руководств по рецептам \"Claude\"","summary":"Anthropic выпустила сборник 'рецептов Claude', включающий несколько руководств, охватывающих сценарии от воспроизведения эталонных результатов поиска агента Claude до создания асинхронной команды нескольких агентов и развертывания продакшн-уровневых агентов. Руководства также охватывают практические аспекты работы с хранилищем Memory, циклом самопроверки Outcomes и миграцией с OpenAI Agents SDK.","category":"技巧观点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic выпустила сборник руководств по рецептам \"Claude\" - Aioga Новости ИИ","description":"Anthropic выпустила сборник 'рецептов Claude', включающий несколько руководств, охватывающих сценарии от воспроизведения эталонных результатов поиска агента Claude до создания асин...","url":"https://www.aioga.com/ru/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:26:35.606Z"},"ar":{"title":"أنتروبك تطلق مجموعة دروس 'وصفات كلود'","summary":"أطلقت Anthropic مجموعة \"وصفات Claude\"، والتي تتضمن العديد من الدروس، تغطي من إعادة إنتاج نتائج معيار البحث لوكيل Claude الذكي إلى بناء فرق متعددة الوكلاء بطريقة غير متزامنة، ونشر وكلاء على مستوى الإنتاج، ومختلف السيناريوهات الأخرى. كما تتناول الدروس أيضًا موضوع تخزين الذاكرة، وحلقة التحقق الذاتي للنتائج، والانتقال من OpenAI Agents SDK، وما إلى ذلك من محتوى عملي.","category":"技巧观点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"أنتروبك تطلق مجموعة دروس 'وصفات كلود' - Aioga أخبار الذكاء الاصطناعي","description":"أطلقت Anthropic مجموعة \"وصفات Claude\"، والتي تتضمن العديد من الدروس، تغطي من إعادة إنتاج نتائج معيار البحث لوكيل Claude الذكي إلى بناء فرق متعددة الوكلاء بطريقة غير متزامنة، ونشر و...","url":"https://www.aioga.com/ar/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:27:42.585Z"},"hi":{"title":"Anthropic ने 'Claude रेसिपी' ट्यूटोरियल संग्रह प्रकाशित किया","summary":"Anthropic ने \"Claude रेसिपी\" संग्रह जारी किया, जिसमें कई ट्यूटोरियल शामिल हैं, जो Claude एजेंट की बेंचमार्क स्कोर को पुनःप्रसारित करने से लेकर असिंक्रोनस मल्टी-एजेंट टीम बनाने, प्रोडक्शन-ग्रेड एजेंट तैनात करने जैसे परिदृश्यों को कवर करते हैं। ट्यूटोरियल में Memory स्टोरेज, Outcomes सेल्फ-वैलिडेशन लूप, और OpenAI Agents SDK से माइग्रेशन जैसे व्यावहारिक सामग्री भी शामिल हैं।","category":"技巧观点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic ने 'Claude रेसिपी' ट्यूटोरियल संग्रह प्रकाशित किया - Aioga AI समाचार","description":"Anthropic ने \"Claude रेसिपी\" संग्रह जारी किया, जिसमें कई ट्यूटोरियल शामिल हैं, जो Claude एजेंट की बेंचमार्क स्कोर को पुनःप्रसारित करने से लेकर असिंक्रोनस मल्टी-एजेंट टीम बनाने, प्र...","url":"https://www.aioga.com/hi/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:27:28.051Z"},"it":{"title":"Anthropic pubblica la raccolta di tutorial 'Ricette di Claude'","summary":"Anthropic ha pubblicato la raccolta di 'ricette' Claude, che include numerosi tutorial, coprendo scenari che vanno dalla riproduzione dei punteggi di benchmark di ricerca dell'agente Claude alla costruzione di team multi-agente asincroni e al deployment di agenti a livello di produzione. I tutorial trattano anche contenuti pratici come l'archiviazione della memoria, il ciclo di autovalidazione degli Outcomes e la migrazione dall'OpenAI Agents SDK.","category":"技巧观点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic pubblica la raccolta di tutorial 'Ricette di Claude' - Aioga Notizie IA","description":"Anthropic ha pubblicato la raccolta di 'ricette' Claude, che include numerosi tutorial, coprendo scenari che vanno dalla riproduzione dei punteggi di benchmark di ricerca dell'agen...","url":"https://www.aioga.com/it/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:28:54.946Z"},"nl":{"title":"Anthropic publiceert de 'Claude-recepten' handleidingcollectie","summary":"Anthropic heeft de \"Claude-recepten\"-collectie uitgebracht, met meerdere tutorials die verschillende scenario's behandelen, van het reproduceren van Claude-agent benchmark scores tot het bouwen van asynchrone multi-agent teams en het implementeren van productieklare agents. De tutorials behandelen ook praktische inhoud zoals geheugenopslag, outcomes self-verification loops en migratie van het OpenAI Agents SDK.","category":"技巧观点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic publiceert de 'Claude-recepten' handleidingcollectie - Aioga AI-nieuws","description":"Anthropic heeft de \"Claude-recepten\"-collectie uitgebracht, met meerdere tutorials die verschillende scenario's behandelen, van het reproduceren van Claude-agent benchmark scores t...","url":"https://www.aioga.com/nl/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:28:31.899Z"},"tr":{"title":"Anthropic 'Claude Tarifleri' eğitim koleksiyonu yayınladı","summary":"Anthropic, birden fazla eğitim içeren 'Claude Tarifleri' koleksiyonunu yayınladı; bu eğitimler, Claude yapay zekâ ajanının arama kıyaslama puanlarını yeniden üretmekten, eşzamanlı çok ajanlı ekipler kurmaya ve üretim düzeyinde ajanları dağıtmaya kadar çeşitli senaryoları kapsıyor. Eğitimler ayrıca Memory depolama, Outcomes kendi kendini doğrulama döngüsü ve OpenAI Agents SDK'dan geçiş gibi uygulamalı içerikleri de içeriyor.","category":"技巧观点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic 'Claude Tarifleri' eğitim koleksiyonu yayınladı - Aioga AI Haberleri","description":"Anthropic, birden fazla eğitim içeren 'Claude Tarifleri' koleksiyonunu yayınladı; bu eğitimler, Claude yapay zekâ ajanının arama kıyaslama puanlarını yeniden üretmekten, eşzamanlı...","url":"https://www.aioga.com/tr/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:29:46.110Z"},"vi":{"title":"Anthropic phát hành bộ sưu tập hướng dẫn 'Công thức Claude'","summary":"Anthropic phát hành bộ sưu tập 'công thức Claude', bao gồm nhiều hướng dẫn, từ việc tái hiện điểm chuẩn tìm kiếm của Claude đến xây dựng đội nhóm đa tác nhân bất đồng bộ, triển khai tác nhân cấp sản xuất và các kịch bản khác. Hướng dẫn cũng bao gồm lưu trữ Memory, vòng tự xác thực Outcomes và chuyển đổi từ OpenAI Agents SDK, cùng các nội dung thực hành khác.","category":"技巧观点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic phát hành bộ sưu tập hướng dẫn 'Công thức Claude' - Tin tức AI Aioga","description":"Anthropic phát hành bộ sưu tập 'công thức Claude', bao gồm nhiều hướng dẫn, từ việc tái hiện điểm chuẩn tìm kiếm của Claude đến xây dựng đội nhóm đa tác nhân bất đồng bộ, triển kha...","url":"https://www.aioga.com/vi/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:29:52.301Z"},"id":{"title":"Anthropic merilis kumpulan tutorial 'resep' Claude","summary":"Anthropic merilis kumpulan 'Resep Claude', yang mencakup berbagai tutorial, dari mereplikasi skor tolok ukur pencarian agen Claude hingga membangun tim multi-agen asinkron, menerapkan agen tingkat produksi, dan sebagainya. Tutorial juga mencakup penyimpanan Memori, siklus self-verifikasi Outcomes, serta praktik migrasi dari OpenAI Agents SDK.","category":"技巧观点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic merilis kumpulan tutorial 'resep' Claude - Berita AI Aioga","description":"Anthropic merilis kumpulan 'Resep Claude', yang mencakup berbagai tutorial, dari mereplikasi skor tolok ukur pencarian agen Claude hingga membangun tim multi-agen asinkron, menerap...","url":"https://www.aioga.com/id/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:30:41.186Z"},"th":{"title":"Anthropic เปิดตัวชุดบทเรียน 'Claude สูตรอาหาร'","summary":"Anthropic เปิดตัวคอลเลกชัน \"Claude Recipes\" ซึ่งประกอบด้วยบทเรียนหลายบทที่ครอบคลุมตั้งแต่การทำซ้ำคะแนนมาตรฐานการค้นหาของเอเจนต์ Claude ไปจนถึงการสร้างทีมเอเจนต์หลายคนแบบอะซิงโครนัส การปรับใช้เอเจนต์ระดับการผลิต ฯลฯ บทเรียนยังเกี่ยวข้องกับการจัดเก็บ Memory, วงจรการตรวจสอบตนเองของ Outcomes และการย้ายจาก OpenAI Agents SDK เป็นต้น","category":"技巧观点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic เปิดตัวชุดบทเรียน 'Claude สูตรอาหาร' - ข่าว AI Aioga","description":"Anthropic เปิดตัวคอลเลกชัน \"Claude Recipes\" ซึ่งประกอบด้วยบทเรียนหลายบทที่ครอบคลุมตั้งแต่การทำซ้ำคะแนนมาตรฐานการค้นหาของเอเจนต์ Claude ไปจนถึงการสร้างทีมเอเจนต์หลายคนแบบอะซิงโครนัส...","url":"https://www.aioga.com/th/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:30:55.819Z"},"pl":{"title":"Anthropic wydaje zbiór przewodników 'Claude Recipes'","summary":"Anthropic opublikował zbiór „przepisów Claude”, zawierający wiele samouczków, obejmujących scenariusze od odtwarzania wyników benchmarków wyszukiwania agenta Claude, po budowanie asynchronicznych zespołów wieloagentowych i wdrażanie agentów klasy produkcyjnej. Samouczki dotyczą również przechowywania pamięci, cyklu autoweryfikacji wyników (Outcomes) oraz praktycznych kwestii związanych z migracją z OpenAI Agents SDK.","category":"技巧观点","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Anthropic wydaje zbiór przewodników 'Claude Recipes' - Aioga Wiadomości AI","description":"Anthropic opublikował zbiór „przepisów Claude”, zawierający wiele samouczków, obejmujących scenariusze od odtwarzania wyników benchmarków wyszukiwania agenta Claude, po budowanie a...","url":"https://www.aioga.com/pl/news/cmrywwsva05zhrolgzua9cma2/","contentTranslated":true,"sourceHash":"7700cb1941cc80c2","translatedAt":"2026-07-27T08:31:42.392Z"}}}}