클로드 쿡북: 고급 AI 에이전트 개발 가이드

Programmatic tool calling (PTC) Reduce latency and token consumption by letting Claude write code that calls tools programmatically in the code execution environment. Tool search with embeddings Scale Claude applications to thousands of tools using semantic embeddings for dynamic tool discovery. Automatic context compaction Manage context limits in long-running agentic workflows by automatically compressing conversation history. Giving Claude a crop tool for better image analysis Give Claude a crop tool to zoom into image regions for detailed analysis of charts, documents, and diagrams. Prompting for frontend aesthetics Guide to prompting Claude for distinctive, polished frontend designs avoiding generic aesthetics. Introduction to Claude Skills Create documents, analyze data, automate workflows with Claude's Excel, PowerPoint, PDF skills. All Cookbooks All Categories Title Categories Author(s) Date Reproduce Claude's agentic search benchmark scores in the Messages API Jun 2026 • Evals Tools Build a Messages API harness that reproduces published DeepSearchQA and BrowseComp scores, using programmatic tool calling, server-side compaction, and task budgets. Evals Tools Mengting Li Jun 2026 Classifier fallback and billing for Claude Fable 5 Jun 2026 • Responses Safeguards Billing 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. Responses Safeguards Billing Alexander Bricken Mahesh Murag Mikaela Grace Jun 2026 Async multi-agent orchestration Jun 2026 • Agent Patterns 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. Agent Patterns Paul Chen Jun 2026 Hosting your agent May 2026 • Claude Agent SDK 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. Claude Agent SDK Kevin Tang Anav Sharma May 2026 Multiagent: coordinate a specialist team May 2026 • Claude Managed Agents Tools 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. Claude Managed Agents Tools Mark Nowicki May 2026 Outcomes: agents that verify their own work May 2026 • Claude Managed Agents Evals 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. Claude Managed Agents Evals Mark Nowicki Gagan Bhat May 2026 Build agents that remember your users Apr 2026 • Claude Managed Agents Tools Give your Claude Managed Agents a Memory store so they learn and remember your users' preferences across multiple interactions. Claude Managed Agents Tools Gagan Bhat Apr 2026 The vulnerability detection agent Apr 2026 • Claude Agent SDK Cybersecurity 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. Claude Agent SDK Cybersecurity Eugene Yan Apr 2026 Build an SRE incident response agent with Claude Managed Agents Apr 2026 • Claude Managed Agents Observability 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. Claude Managed Agents Observability Gagan Bhat Apr 2026 Build a data analyst agent with Claude Managed Agents Apr 2026 • Claude Managed Agents Tools Build an analyst that turns a CSV into a narrative HTML report with interactive charts, using a sandboxed environment and file mounting. Claude Managed Agents Tools Charmaine Lee Jess Yan Apr 2026 Build a Slack data analyst bot with Claude Managed Agents Apr 2026 • Claude Managed Agents Integrations Mention the bot with a CSV to get an analysis report in-thread, with multi-turn follow-ups on the same session. Claude Managed Agents Integrations Charmaine Lee Apr 2026 Managed Agents tutorial: iterate on a failing test suite Apr 2026 • Claude Managed Agents Tools 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. Claude Managed Agents Tools Paul Yang Apr 2026 Managed Agents tutorial: production setup Apr 2026 • Claude Managed Agents Integrations 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. Claude Managed Agents Integrations Paul Yang Apr 2026 Managed Agents tutorial: prompt versioning and rollback Apr 2026 • Claude Managed Agents Evals 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. Claude Managed Agents Evals Mark Nowicki Apr 2026 Threat intelligence enrichment agent Apr 2026 • Tools Agent Patterns Cybersecurity 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. Tools Agent Patterns Cybersecurity Jannet Park Apr 2026 Building a session browser Mar 2026 • Claude Agent SDK Agent Patterns List, read, rename, tag, and fork Agent SDK sessions on disk to build a conversation history sidebar without writing a transcript parser. Claude Agent SDK Agent Patterns Qing Wang Mar 2026 Knowledge graph construction with Claude Mar 2026 • RAG & Retrieval Tools Build knowledge graphs from unstructured text using Claude for entity extraction, relation mining, deduplication, and multi-hop graph querying. RAG & Retrieval Tools Anthropic Mar 2026 Context engineering: memory, compaction, and tool clearing Mar 2026 • Tools Agent Patterns Compare context engineering strategies for long-running agents and learn when each applies, what it costs, and how they compose. Tools Agent Patterns Isabella He Mar 2026 Migrating from the OpenAI Agents SDK Mar 2026 • Claude Agent SDK Agent Patterns 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. Claude Agent SDK Agent Patterns Preston Tuggle Mar 2026 The site reliability agent Feb 2026 • Claude Agent SDK Agent Patterns Build an incident response agent with read-write MCP tools for autonomous diagnosis, remediation, and post-mortem documentation. Claude Agent SDK Agent Patterns Ben Lehrburger Isabella He Feb 2026 Session memory compaction Jan 2026 • Agent Patterns Responses Manage long-running Claude conversations with instant session memory compaction using background threading and prompt caching. Agent Patterns Responses Joe Shamon Jan 2026 Programmatic tool calling (PTC) Nov 2025 • Tools Reduce latency and token consumption by letting Claude write code that calls tools programmatically in the code execution environment. Tools Pedram Navid Nov 2025 Tool search with embeddings Nov 2025 • Tools RAG & Retrieval Scale Claude applications to thousands of tools using semantic embeddings for dynamic tool discovery. Too