Turning conversation into knowledge: how Slack builds human-agent teams | Claude by Anthropic

This is the second post in our series on building human-agent teams. The first shared what we've learned building teams with multiplayer AI at Anthropic. In this article, we share best practices from a company that was thinking about human-agent teams long before AI arrived. Jaime Delanghe joined Slack in 2017 to work on search and machine learning, with a mission to turn workplace conversation in

[nguyen-oi]

DMに情報閉じ込めずオープンチャンネルにしてAIに読ませろってのは確かに今の時代っぽい

[kiririmode]

AIエージェントが変えるのは検索性能ではなく、組織知の作り方という話。人間が仕事の後に会話を文書化するモデルから、エージェントが必要な時点で会話履歴から判断理由を再構成するモデルへ

[misshiki]

Slack CPOが語るhuman-agent team論。会話履歴をknowledge base化し、public channelでcontextを共有。Agentが作業、人間が判断するhandoff loopと、小さく始めて利用例を横展開する方法を紹介。