CCDV-F: Claude Certified Developer — Foundations

By Anthropic · Question Mode

QuestionQ59

VerifiedModel Selection and Optimization

You maintain a Claude application that uses Claude Sonnet 4.5 in several production workflows. Anthropic has released Claude Sonnet 4.7, which your evaluation suite shows performing 8% better on your highest-volume task. However, this version produces different output formatting on two of your structured-extraction prompts that downstream consumers parse using regex-based code.

To roll out the upgrade, you would...

Explanation

Explicit format instructions and evaluation against the existing parsing requirements help identify and reduce incompatibilities before deployment. Anthropic recommends specifying the desired output format and testing model changes with actual prompts and data. (platform.claude.com) A feature-flagged rollout with per-workflow rollback limits the impact of unexpected failures while allowing workflows to benefit from the improved model.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!