Track 04 · 15 lessons
AI Product Management.
Choose where AI helps, and design for where it fails.
Completed: What an LLM Actually Does
Understand why useful generation is not the same as verified knowledge.
Scroll lessonCompleted: Tokens, Context and Sampling
Connect model settings to memory, variation, cost, and user expectations.
Scroll lessonCompleted: Choosing a Model
Select for the task and its failure cost, not the leaderboard.
Scroll lessonCompleted: Prompt and Instruction Design
Make the intended behavior explicit and test changes like product changes.
Scroll lessonCompleted: Structured Outputs
Separate predictable format from correct meaning.
Scroll lessonCompleted: Tool Calling
Understand how a model's proposed action becomes a software operation.
Scroll lessonCompleted: RAG
Use retrieval to supply evidence, then evaluate both finding and answering.
Scroll lessonCompleted: Embeddings and Vector Search
Use semantic similarity without confusing it with exactness or truth.
Scroll lessonCompleted: Agents and Workflows
Choose autonomy only where adapting the next step creates value.
Scroll lessonCompleted: Evals
Define quality before the demo persuades you the system is ready.
Scroll lessonCompleted: Hallucinations and Uncertainty
Design around the consequences of plausible but unsupported output.
Scroll lessonCompleted: Human in the Loop
Put review where a person can actually detect and prevent the important error.
Scroll lessonCompleted: AI Cost, Latency and UX
Optimize the time and money spent on a successful user outcome.
Scroll lessonCompleted: AI Safety, Privacy and Data
Ask where information goes and what the system is allowed to do with it.
Scroll lessonCompleted: When NOT to Use AI
Choose the simplest method that can meet the task's correctness requirements.
Scroll lesson