These micro-apps are intentionally not "chatbots" and they aren't "custom GPTs". Those things are great, but too open and unstructured for assessment and organizational use (where costs need to be tightly controlled).
That being said, I have seen several use cases now where the AI gives an output, but the user has to revise that output. I.e. the AI provides a video script but the user says, "cut that down to 500 words" or something.
So I'd like to build in an option to "revise" the output at each stage, and a "max revisions" field.
Here are some user stories.
If the "revisable" option is True, then the user get a "revise" button option after the outputs have been generated by AI. This button shouldn't stop them from going on to the next question. Most of the time, the outputs will not be revised and the user will just move out.
If the student clicks revise, they get a text area that allows them to ask for a change in the outputs.
When submitted, that text gets sent to AI. This happens before the next phase kicks off. So looking at an example, the user asks for a revision of the Ai's first arguments in the debate:
The AI sends a new output for that phase.
This process is repeatable for as many times as the user wants up to the "max revisions" field. Once revisions are used up, the user is forced to accept the output and move on to the next phase.
"Max revisions" is unique to each phase. If phase 1 has 3 revisions and phase 2 has 2 revisions, then the user might use up all three on phase 1...but they'll still have all 2 for phase 2.
These micro-apps are intentionally not "chatbots" and they aren't "custom GPTs". Those things are great, but too open and unstructured for assessment and organizational use (where costs need to be tightly controlled).
That being said, I have seen several use cases now where the AI gives an output, but the user has to revise that output. I.e. the AI provides a video script but the user says, "cut that down to 500 words" or something.
So I'd like to build in an option to "revise" the output at each stage, and a "max revisions" field.
Here are some user stories.