TL;DR — Claude Sonnet 5 is best treated as an agent workflow model. See specs, setup steps, guardrails, examples, and review checks for safer production use today. The gist, in a few bullets: Use it first on bounded workflows where planning, tool use, and review checkpoints matter more than one-shot text generation Recheck token budgets before migration: Anthropic's Platform Docs say the model has a 1M token context window and 128k max output tokens, while the new tokenizer produces a...