Designing agents as if people mattered
Download as PPT, PDF0 likes139 views
1) The document discusses how people form models and expectations about how the world works based on their experiences. For example, a little girl expects that people, not computers, initiate actions like turning off lights. 2) It argues that when designing technologies, we should focus not just on making them smarter but on how they fit into people's lives and match their expectations. 3) The document explores different meanings of the term "agent" - as software with some degree of autonomy, and as a metaphor that shapes how users perceive and interact with a program. An agent model allows for more dynamic and knowledgeable interactions compared to a passive object model.
Designing agents as if people mattered
- 1. Designing Agents as if People Mattered By: Aryan Rathore Head Of Aryan Dell Corporation Jaipur Aryan Computer Organization Jaipur Mob:- 8560089002
- 2. • One of Apple Computer's buildings used to have an advanced energy management system. Among its many features was the ability to make sure lights were not left on when no one was around.
- 3. A dialogue between a little daughter and fatherDaughter: Who turned out the lights? Father: The computer turned off the lights. Daughter: (pause) Did you turn off the lights? Father: No, I told you, the computer turned off the lights. (someone else manually turns the lights back on) Daughter: Make the computer turn off the lights again! Father: (with irony in his voice) It will in a few minutes.
- 4. • She clearly had a model of how the world worked: “people initiate actions; computers don't.”
- 5. • Just like the little girl, we all strive to make sense of our world. • We move through life with sets of beliefs and expectations about how things work. • We try to understand what is happening. • We make up stories about how things work. • We try to change things. • We make predictions about what will happen next. • The degree to which we succeed in doing these things is the degree to which we feel comfortable and in control of our world.
- 6. • The central theme is that we need to focus not just on inventing new technologies, not just on making them smarter, but on designing technologies so that they fit gracefully into our lives.
- 7. What Does "Agent" Mean? • "Agent" is the locus of considerable confusion. • 2 ways of agents’ meaning description.
- 8. adaptive functionality • An agent is a program that is, • to some degree, • capable of initiating actions, • forming its own goals, • constructing plans of action, • communicating with other agents, • and responding appropriately to events--all without being directly controlled by a human.
- 9. agent metaphor. • “what is portrayed to the user” • The agent metaphor suggests a particular model of what the program is, how it relates to the user, and its capabilities and functions.
- 10. Adaptive Functionality • In general, systems with adaptive functionality are doing three things: • noticing: trying to detect potentially relevant events • interpreting: trying to recognize the events (generally, this means mapping the external event into an element in the system's 'vocabulary') by applying a set of recognition rules • responding: acting on the interpreted events by using a set of action rules, either by taking some action that affects the user, or by altering their own rules (i.e. learning)
- 11. Design issues by adaptive functionality • Understanding: What Happened and Why? • Control: How can I Change It? • Prediction: Will it Do What I Expect?
- 12. The Agent Metaphor • Reactions and Expectations • Guides • Computers as social actors • Faces
- 13. The Object-Action Conceptual Model • Some of the general knowledge that is most relevant to the objects found in graphic user interfaces includes the following: • objects are visible • objects are passive • objects have locations • objects may contain things
- 14. The Agent Conceptual Model • Consider some of the general knowledge people have about agents: • agents can notice things • agents can carry out actions • agents can know things • agents can go places This
- 15. Object-Action vs Agents Conceptual Model • Rather than passive objects that are acted upon, the agent metaphor's basic components (agents, of course) have a degree of animacy and thus can respond to events.
- 16. Object-Action vs Agents Conceptual Model • Agents can go places. • Users expect objects to stay where they're put; • agents, on the other hand, are capable of moving about. • Where can agents go? That depends both on the particular portrayal of the agent, as well as on the spatial metaphor of the interface.
- 17. Object-Action vs Agents Conceptual Model • While objects can contain things, agents know things, hence can learn things. • Thus, the agent conceptual model is suitable for representing systems which • acquire, • contain, • and manage knowledge. • What sort of things are agents expected to learn or know? That depends on the way in which the agent is portrayed.