blackboard system

A problem-solving architecture organized around a shared, structured workspace — the blackboard — on which a solution is assembled piece by piece, often across a hierarchy of abstraction levels (for speech: sound segments, syllables, words, phrases), by independent modules called knowledge sources that never call one another directly. A knowledge source is triggered when the blackboard reaches a state it knows how to extend, and a control component chooses which triggered contribution to apply next, opportunistically mixing data-driven and goal-driven reasoning. The design fits messy problems whose solution draws on varied, partial and sometimes conflicting expertise, such as speech understanding, sonar interpretation and protein-structure determination. In the mid-2020s researchers revisited the pattern for multi-agent systemsmulti-agent system, n.: A setup in which several AI agents, each with its own role or point of view, work together — or compete — on a problem, passing messages and results among themselves. built on language modelslarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code., letting agentsAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done. coordinate through a shared workspace rather than by messaging one another directly.