Practice · 2022–2025 · AI Present

Prompt engineering

Craft the magic string until the model behaves. Job title of 2023; table-stakes skill of 2026.

Prompt engineering mutated from a specialty into ordinary product work — versioned prompts, evals, and tool schemas. It failed as a standalone career when models improved and templates commoditized. The durable residue is treating prompts like code with tests.

Patterns

Context

Demos consolidate; evals remain

AI pair programming changed how code is typed faster than how it is reviewed. Agent frameworks and standalone vector stores sorted into demos versus durable plumbing; mid-market RAG folded back into Postgres. The permanent layer is familiar: evals that gate deploys, model routing for cost, tool protocols instead of plugin snowflakes, and humans who own production. Autopilot rewrites and vibe-shipped auth middleware are still big-bang migrations with better slides — and a longer on-call.

Compare with

Related

© 2026 Fadstack · Shane Code

Opinionated history · not a ranking