Prompt Engineering Fundamentals: Write Instructions Models Follow
by Laura Mbeki
Catalog
Programming, AI and prompt-engineering courses written by working engineers. Filter by language, level, price or rating — buy once, get an instant email access link, keep it for life.
Jump to a technology
Showing 25–40 of 40 courses
Understand why models drift, then write instructions that hold across a long conversation.
Get valid JSON on the first attempt, and handle the cases where you still will not.
Fit the right material into a context window and cut token spend without losing accuracy.
Design tool schemas a model calls correctly, and handle the failures when it does not.
Build a small eval suite that tells you honestly whether a prompt change was an improvement.
Move from clever one-off prompts to versioned, tested prompt systems a team can maintain.
Your first month with model APIs: keys, streaming, retries, cost and one shipped feature.
Understand embeddings well enough to build search that finds meaning, not just keywords.
Chunking, hybrid search and reranking, the parts that decide whether retrieval really works.
Pick, index and operate a vector store without turning your search into a science project.
Make assistants a genuine part of your workflow, not a party trick abandoned by Friday.
Write joins, aggregates and filters you can defend, starting from a completely blank slate.
Running totals, rankings and gaps-and-islands, explained until they finally feel obvious.
Indexes, transactions, JSONB and migrations, taught from the application developer seat.
Containerise a real application, then run its entire stack locally with one Compose file.
Pipelines that run fast, cache correctly and fail for reasons you can actually read.