The reason I developed a communication model for AI-powered chatbots is to encourage and guide a human-centered approach to the implementation of AI-powered services and products. You can think of it as a tool that helps you better consider inclusive design, trustworthiness and safety.
Tech tools can be powerful and useful, and the chances of that are greater when we understand and design for improved human-machine interplay. Without this, even tools with the potential to solve significant problems can easily be rejected.
For example, these are the types of circumstances that will affect how a human approaches and begins using a tool:
Expectations.
How have the person's expectations been formed and how well do they match what is possible in the given situation? How can we help keep these expectations at a good level?
Ability.
Given the person's experience, knowledge and physical and cognitive capacity, how well equipped is the person to interact with the computer - for example, when it comes to phrasing inputs and prompts in a way that makes the computer produce a result they are satisfied with. How do we ensure that the tool is adapted to the operator's ability?
Context.
What context is the person currently in and might this, for example, affect their ability to act as they themselves would like. How do we work with understanding context and taking this into account?
Intent.
Does the person have an intent that we can subsequently check and verify. How do we help the operator phrase their intent?
Code.
Can the person encode their intention, linguistically, in a way that makes it, for example, distinct or useful to the computational model in a way that minimizes ambiguity. What support can help make the coding of the question more accurate?
Expression.
Does the input contain an expression that can affect the computational model in any direction? For example, this could pertain to formal, casual or childish language. How permissive or guiding should the tool be regarding these expressions?
The model goes on to describe ways of managing a computational model, in terms of "black box" characteristics, interpretation and computation (over truth).
Managing the response from the AI-powered service brings with it further parameters that we need to consider.
My communication model is free to use, and all of its components are described in my post. If you need more design assistance and advice when managing organisational change brought on by tech, you know where to find me. 😊