Practice · 2022–2025 · AI Present
Prompt engineering
Craft the magic string until the model behaves. Job title of 2023; table-stakes skill of 2026.
How Prompt engineering mutated
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
Compare with
Related
Framework · 2023–now
LLM app frameworks
LangChain-class glue mutated into MCP clients and thin wrappers around vendor APIs. The durable pieces are still boring: evals, retrieval, and product UX.
Practice · 2023–now
LLM eval pipelines
Regression tests for nondeterministic models that actually fail the build. The unglamorous CI that separates demos from products.
Practice · 2021–now
AI pair programming
Coding agents that edit the repo — now table stakes. Generation outran review capacity; ownership is the bottleneck.
Practice · 2025–now
Agent skills / SKILL.md
Packaged workflows in a folder — name, description, scripts — loaded on demand instead of stuffing the system prompt.