Claude Cookbook

Summary

Reproduce Claude's agentic search benchmark scores in the Messages APIBuild a Messages API harness that reproduces published DeepSearchQA and BrowseComp scores, using programmatic tool calling, server-side compaction, and task budgets.EvalsToolsMengting LiJun 2026Classifier fallback and billing for Claude Fable 5Jun 2026•ResponsesSafeguardsBillingDetect 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.ResponsesSafeguardsBillingAlexander BrickenMahesh MuragMikaela GraceJun 2026Async multi-agent orchestrationTwo 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 PatternsPaul ChenJun 2026Hosting your agentMay 2026•Claude Agent SDKDeploy 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 SDKKevin TangAnav SharmaMay 2026Multiagent: coordinate a specialist teamMay 2026•Claude Managed AgentsToolsHeterogeneous 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 AgentsToolsMark NowickiMay 2026Outcomes: agents that verify their own workMay 2026•Claude Managed AgentsEvalsBuild 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 Ag...