Re: [webai] Human Judgment Layer – A Missing Piece? (#7)

The Amazon scenario reminds me of Autonomy AgentWare Web Researcher, released around 1996 by Autonomy Systems Ltd. in Cambridge, UK. It was an early intelligent web search agent using neural networks and Bayesian inference for meaning-based searching via pattern recognition rather than keywords. The model was represented as a cartoonish dog agent and users trained it with natural language descriptions of topics. They could be hosted and launched from virtual kennels to autonomously and asynchronously roam the web overnight,. The playful interface displayed search progress graphically, allowed drag-and-drop agent deployment, and refined searches through user feedback on graded document lists to build a personal library. Only 3O years ago :)

-- 
GitHub Notification of comment by FabienGandon
Please view or discuss this issue at https://github.com/w3c/webai/issues/7#issuecomment-3899592891 using your GitHub account


-- 
Sent via github-notify-ml as configured in https://github.com/w3c/github-notify-ml-config

Received on Friday, 13 February 2026 21:30:14 UTC