AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻譯準備中
一個結構化、驗證過的知識程式碼語料庫,讓人類與 AI 會話皆可閱讀與貢獻,且由工具維持其形狀。
AI 翻譯
A structured, validated knowledge corpus that people and AI sessions both read from and contribute to, and the tool that holds it to its shape.
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Knowledge as Code (KaC) is a framework for knowledge that people and AI sessions both read from and contribute to. It is
plain Markdown in git, reviewed by pull request. But every document has a type, and every type declares a schema.
kac is the tool that checks each document against the schema its type declares. It reports every fault against the
file that caused it. A broken cross-reference fails CI. kac writes the indexes and tables nobody should be keeping by
hand. It also writes the documents out as an export: data an agent can read.檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
Knowledge as Code (KaC) is a framework for knowledge that people and AI sessions both read from and contribute to. It is
plain Markdown in git, reviewed by pull request. But every document has a type, and every type declares a schema.
kac is the tool that checks each document against the schema its type declares. It reports every fault against the
file that caused it. A broken cross-reference fails CI. kac writes the indexes and tables nobody should be keeping by
hand. It also writes the documents out as an export: data an agent can read.檢視完整 README ↗