77 minutesAI prompt engineering: A deep dive
Hear how production prompt engineers revise instructions, examples and behavioral constraints under real pressure instead of treating prompts as one-off text.
Play videoLenny's Podcast. Hamel Husain and Shreya Shankar walk through the entire eval workflow on a real property-management AI assistant — looking at traces, open and axial coding of errors, deciding when to stop, building an LLM-as-judge, and validating it against human judgment. This is the rare long-form conversation that is genuinely aimed at PMs and team leads rather than ML engineers, and complements the article's requirement for an owned review cadence tied to changes, incidents and observed failures.
This remains one of the best non-engineer eval explanations because it focuses on workflow discipline rather than a specific tool. Keep the method, then choose tooling that fits your privacy and observability constraints.
Learn the product-builder eval loop: inspect traces, label failures, define criteria, test changes and compare against human judgment.
Have at least one AI workflow where quality can get better or worse over time.
Last reviewed: May 18, 2026
Continue through the same learning path with the next curated companion videos.
77 minutesHear how production prompt engineers revise instructions, examples and behavioral constraints under real pressure instead of treating prompts as one-off text.
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.
Hand-picked external courses that go deeper on this topic.
Brenna Zenaty, Adriti Gulati
Made directly for support and customer-success teams. HubSpot Academy is free, well-produced, and refreshingly concrete — it walks through AI-assisted ticket triage and a knowledge-base agent rather than staying abstract, and the certificate is free too, not a paywall bait-and-switch.
Crystal King and HubSpot Academy
The marketing vertical gap, filled by a genuinely free, well-instructed course rather than a paywalled Udemy clone. It's honest about limitations and ethics (a full lesson on bias, transparency, and IP) instead of just cheerleading AI content generation, which matches our editorial standard better than most 'AI for marketers' filler out there.
Robert Flemister
Sales is the other vertical we had nothing for. This is short by design — two lessons, 36 minutes — and stays concrete: lead scoring, AI-drafted outreach at scale, and deal-risk signals, rather than a vague promise that 'AI will transform your pipeline.' A quick, credible entry point for individual reps, not just sales-ops leadership.