# Agent–Computer–Human Interaction

> Agent–Computer–Human Interaction = Agent-computer interaction + Human-computer interaction

Agent–Computer–Human Interaction = [Agent-computer interaction](https://wiki.g15e.com/pages/Agent-computer%20interaction.txt) + <Human-computer interaction>

Fragments of thought about how the existing <HCI> paradigm might change, assuming that infrastructure for [Agent-computer interaction](https://wiki.g15e.com/pages/Agent-computer%20interaction.txt), such as [MCP](https://wiki.g15e.com/en/pages/Model%20context%20protocol.txt), becomes commonplace and foundational technologies such as [LLMs](https://wiki.g15e.com/en/pages/Large%20language%20model.txt) are widely available.

The [conversational user interface](https://wiki.g15e.com/pages/Conversational%20user%20interface.txt), which has remained popular since [ChatGPT](https://wiki.g15e.com/en/pages/ChatGPT.txt), is not a particularly good UI.

## Assumptions

[Agent-computer interaction](https://wiki.g15e.com/pages/Agent-computer%20interaction.txt), including [MCP](https://wiki.g15e.com/en/pages/Model%20context%20protocol.txt), becomes commonplace. What does commonplace mean?

- Remote MCP servers become sufficiently diverse, or tools such as <Playwright MCP> and [OmniParser](https://wiki.g15e.com/pages/OmniParser.txt) (now that I write this down, both came from <Microsoft>) enable [AI agents](https://wiki.g15e.com/en/pages/AI%20agent.txt) to use existing systems better.
- There is a well-maintained directory of trustworthy service providers (an MCP registry? MCP discovery service?).
- The practical requirements for serious use of MCP and similar technologies—security, authentication, billing, and so on—are in place.

Foundational technologies such as [LLMs](https://wiki.g15e.com/en/pages/Large%20language%20model.txt) become widely available. What does widely available mean?

- The cost of using a sufficiently capable [LLM](https://wiki.g15e.com/en/pages/Large%20language%20model.txt) approaches zero.

(What else? <ToDo>)

## Revisiting the existing paradigm

Revisit the research at <Xerox PARC>. In particular, examine which assumptions they made still hold, which no longer hold, and which could be reconsidered, and develop ideas from there.

Possible topics to reconsider:

- **Humans**: Humans themselves have not changed biologically at all. But 1) <cognitive psychology> was in its infancy then, leaving considerable room to reconsider the psychological principles used at the time in light of developments in [embodied cognition](https://wiki.g15e.com/en/pages/Embodied%20cognition.txt), [personality psychology](https://wiki.g15e.com/en/pages/Personality%20psychology.txt), <emotional psychology>, and other fields; and 2) even if human biology has not changed, we need to consider how greatly our social context has changed (<the internet>, <social media>, etc.).
- **Computers**: We need to consider the enormous gains in computer performance (computation speed, network transmission speed, storage capacity, and so on), the spread of <XR> devices, advances in [neural-network](https://wiki.g15e.com/en/pages/Artificial%20neural%20network.txt)-based [generative AI](https://wiki.g15e.com/en/pages/Generative%20AI.txt) such as [LLMs](https://wiki.g15e.com/en/pages/Large%20language%20model.txt), and the spread of the <internet of things>.

(<ToDo>)

Reference:

- [Premature death of UI design](https://wiki.g15e.com/en/pages/Premature%20death%20of%20UI%20design.txt)

## Fragments of a new paradigm

(<ToDo>)

## See also

- [LLM OS](https://wiki.g15e.com/pages/LLM%20OS.txt)
- [Definition of design](https://wiki.g15e.com/en/pages/Definition%20of%20design.txt)
- [Specification written in natural language](https://wiki.g15e.com/en/pages/Specification%20written%20in%20natural%20language.txt)