My AI workflow evolved from prompts to a near-autonomous workflow
hackernews
|
|
🔬 연구
#ai
#ai devkit
#automation
#coding
#review
#workflow
#워크플로
#자율화
#코딩
#프롬프트
원문 출처: hackernews · Genesis Park에서 요약 및 분석
요약
최근 6개월간 AI 코딩 워크플로우를 고도화한 결과, 단순한 프롬프트 최적화를 넘어 맥락을 유지하고 작업을 자동 검증하는 준자율적(near-autonomous) 워크플로우를 구축했습니다. 개발자는 단 한 문장의 지시만 내렸을 뿐인데도 시스템이 요구사항 정의, 설계, 구현, 테스트, 코드 리뷰의 전 과정을 약 30분 만에 완벽하게 수행했습니다. 특히 구현 과정에서 설계와의 괴리를 발견해 수정하거나 과거 기억을 불러오는 등 워크플로우가 주도적인 역할을 하며 요구사항 명세서와 테스트 코드 등의 구체적 결과물을 남겼습니다. 결국 AI가 단순한 코드 생성기가 아닌 체계적인 업무 프로세스로 자리 잡으면서, 향후 AI 활용의 핵심은 모델 자체보다 이를 둘러싼 워크플로우 계층을 최적화하는 것으로 변화하고 있습니다.
본문
Over the last 6 months, I have been evolving my AI coding workflow while building AI DevKit.<p>The shift that mattered most was not better code generation. It was moving from reusable commands and templates into a workflow that can carry context, trigger the right behavior, and verify work automatically.</p><p>A recent feature made the difference obvious. I used Codex to build interactive skill selection for "ai-devkit skill add". I gave one sentence of instruction, and the workflow carried the task through requirements, design, planning, implementation, verification, tests, and code review.</p><p>The whole session took under an hour. The actual feature flow was around 30 minutes.</p><p>What I found interesting was not just that AI wrote code. It was that the workflow left behind requirements, design docs, planning artifacts, tests derived from requirements, and verification against the spec instead of just a diff.</p><p>A few things that felt important in practice:</p><p>- memory pulled back an old CLI rule I had forgotten I stored
- review phases could loop backward instead of blindly moving forward
- verification caught drift between implementation and design
- I still made the product decisions and fixed the last failing test myself</p><p>I am curious how others here are thinking about this.</p><p>Are you mostly optimizing prompts, or are you now trying to optimize the workflow layer around the model?</p>
- review phases could loop backward instead of blindly moving forward
- verification caught drift between implementation and design
- I still made the product decisions and fixed the last failing test myself</p><p>I am curious how others here are thinking about this.</p><p>Are you mostly optimizing prompts, or are you now trying to optimize the workflow layer around the model?</p>
Genesis Park 편집팀이 AI를 활용하여 작성한 분석입니다. 원문은 출처 링크를 통해 확인할 수 있습니다.
공유