New Claude Cookbook guides cover search benchmarks, safety fallbacks, and multi-agent patterns
Anthropic added several technical guides to the Claude Cookbook in June 2026. Mengting Li's walkthrough shows how to build a Messages API harness that reproduces the published DeepSearchQA and BrowseComp scores using programmatic tool calls, server-side compaction, and task budgets.
A second guide breaks down what happens when the safety classifier fires on Claude Fable 5 and how to fall back to Opus 4.8, either server-side or client-side through the SDK, accounting for streaming behavior and the latest billing changes.
A third guide from Paul Chen reduces two async multi-agent patterns to their basic mechanics: a fixed team of N agents passing messages through a shared hub, and dynamically spawned async subagents.
Related stories
- Claude Managed Agents can now hand tasks off to each other
- Claude helped make claude.ai 3x faster in two weeks
- Claude system prompts documentation updated
- Opus 5.5 costs less and answers old agent code with 400s
- Delete "think carefully" from your Opus 5.5 prompts
- Opus 5.5 finds new bugs for CodeRabbit and misses old ones
Comments
No comments yet. Be the first.
Join the conversation
Sign in with Google to leave a comment. Your name and avatar come from your Google profile, and the comment appears after moderation.