Ai First Engineering

1---2name: ai-first-engineering3description: Engineering operating model for teams where AI agents generate a large share of implementation output.4origin: ECC5---6 7# AI-First Engineering8 9Use this skill when designing process, reviews, and architecture for teams shipping with AI-assisted code generation.10 11## Process Shifts12 131. Planning quality matters more than typing speed.142. Eval coverage matters more than anecdotal confidence.153. Review focus shifts from syntax to system behavior.16 17## Architecture Requirements18 19Prefer architectures that are agent-friendly:20- explicit boundaries21- stable contracts22- typed interfaces23- deterministic tests24 25Avoid implicit behavior spread across hidden conventions.26 27## Code Review in AI-First Teams28 29Review for:30- behavior regressions31- security assumptions32- data integrity33- failure handling34- rollout safety35 36Minimize time spent on style issues already covered by automation.37 38## Hiring and Evaluation Signals39 40Strong AI-first engineers:41- decompose ambiguous work cleanly42- define measurable acceptance criteria43- produce high-signal prompts and evals44- enforce risk controls under delivery pressure45 46## Testing Standard47 48Raise testing bar for generated code:49- required regression coverage for touched domains50- explicit edge-case assertions51- integration checks for interface boundaries