Designing prompts for production — companion videos

Anthropic

Four Anthropic prompt engineers (research, alignment, applied, developer relations) talking at length about what they actually do day to day — how they edit prompts under pressure, how they think about "honesty" in instructions, when XML scaffolds help, when they don't. The article's layered model maps cleanly onto how they describe the work; this is the best way to hear that mental model out loud.

What you should get from this: Hear how production prompt engineers revise instructions, examples and behavioral constraints under real pressure instead of treating prompts as one-off text.

Watch or know first: You should already ship prompts somewhere — it's a practitioner roundtable, not a course.

Anthropic

A live build session by Anthropic's Applied AI team on an insurance-claims prompt — they start with a vague instruction and iterate to something a developer would actually ship, showing the kind of revisions the article describes for the system and developer layers. Watch this before re-reading the article's checklist on examples, output structure, and refusal handling.

What you should get from this: Watch a vague insurance-claims prompt become a structured, testable prompt with clearer examples, output rules and refusal behavior.

Watch or know first: Basic prompting fluency; the article's layer model gives you the right lens.