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
在三個方面降低 AI 編碼代理的 token 成本:簡潔文字、YAGNI‑優先程式碼、以及工具輸出壓縮。Claude Code、Pi、Cursor、Codex、Gemini 等 4 種。零相依,公開基準測試包括其失敗的執行。
AI 翻譯
Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Your AI talks less, builds less, reads less, and says more. Like a senior dev who bills by the syllable.
The only tool in this class that publishes the runs where it lost.
44% of a bare model's output tokens on coding prompts · 11 agents · zero dependencies · one command
chisle.jaypokale.me is the site version of this README, with fewer words
"Add debounce to a search input that currently fires an API call on every keystroke." Same model, same prompt, one difference: the injected ruleset. Both answers below are the verbatim committed output from benchmarks/results/raw/: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。
Your AI talks less, builds less, reads less, and says more. Like a senior dev who bills by the syllable.
The only tool in this class that publishes the runs where it lost.
44% of a bare model's output tokens on coding prompts · 11 agents · zero dependencies · one command
chisle.jaypokale.me is the site version of this README, with fewer words
"Add debounce to a search input that currently fires an API call on every keystroke." Same model, same prompt, one difference: the injected ruleset. Both answers below are the verbatim committed output from benchmarks/results/raw/:檢視完整 README ↗