Engineering Quality
Writing filed under Engineering Quality.
Model retirements made AI maintenance visible
Queues make AI workflows calmer
Caching AI responses with care
Data cleaning is model work
Better data often improves AI systems more than another round of prompt tweaks.
Prompt pipelines need ownership
Evals are how AI teams stay honest
A simple note on using evals to catch regressions before users find them.
Structured Outputs made prompts less magical
Embeddings are product plumbing
Embeddings are useful because they make search, memory, deduping, and retrieval feel less brittle.