9 minutesLangSmith in 10 Minutes
You can navigate traces, projects and datasets in LangSmith and read off token cost, latency, error rate and per-span detail.
Play videoAnthropic. 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.
Treat it like a long podcast — the value is hearing the article's layered mental model described out loud by people who edit prompts under real pressure.
Hear how production prompt engineers revise instructions, examples and behavioral constraints under real pressure instead of treating prompts as one-off text.
You should already ship prompts somewhere — it's a practitioner roundtable, not a course.
Last reviewed: May 18, 2026
Continue through the same learning path with the next curated companion videos.
9 minutesYou can navigate traces, projects and datasets in LangSmith and read off token cost, latency, error rate and per-span detail.
19 minutesImprove tool design so agents select the right action with the right parameters.
13 minutesChoose between prompt engineering, RAG, fine-tuning or a combination based on the actual failure mode.
Hand-picked external courses that go deeper on this topic.
Isa Fulford · Andrew Ng
Ninety minutes to a year's worth of intuition. If you've started writing code that calls an LLM — or you're about to — this is the most efficient course online for closing the gap between "playing with ChatGPT" and "shipping a feature that calls an LLM."
Microsoft Learn
Prompt engineering, but for the tool most office workers will actually touch first. Microsoft's own four-part prompting framework (goal, context, source, expectation) is a genuinely useful mental model, and unlike the generic ChatGPT prompting courses already in our catalog, this one is grounded entirely in Microsoft 365 Copilot's specific quirks and grounding behavior.