IBM 用 Agent Logic 將 token 用量降低30倍 —— 我們還需要前沿模型嗎？
ibm 的 watsonx code assistant 利用 agent logic（靜態分析/知識圖譜）將 token 使用量降低 30 倍，同時保持遺留代碼任務的準確性，表明可擴展的企業 ai 更多依賴軟件定義的引導而非原始模型能力。
ibm detailed how watsonx code assistant for z uses agent logic—software primitives like knowledge graphs and static analysis—to navigate complex enterprise workflows involving legacy cobol and pl/1 code. by pre-indexing application structure into database schemas, the agent retrieves precise information to guide the llm, resulting in roughly 30x lower token usage compared to a baseline frontier model while maintaining superior performance. this challenges the reliance on massive context windows and expensive frontier models, signaling that scalable enterprise adoption requires software-defined steering to manage dynamic workflows and regulatory constraints effectively.