The workflows in JITT are simplified versions of standard business workflows that may exist for the organization, such as a purchasing process or examination script process, except that their nodes may link to metadata about the concepts being dealt with at this point of the workflow.
This means that the user can maintain some level of control over the way that their student model is interpreted by JITT.
The current JITT prototype has two sources of evidence about the user's knowledge.
However, in JITT, the nature of the learning and the use of workflows to define the granularity of learning tasks makes it easier for the teacher to define concepts (and hence metadata) at the right grain size.
The design of JITT and its underlying architecture is intended to exploit existing document bases within organizations.
This means that the teacher has only to invest modest amounts of time in marking up documents and it also means that, in practice, JITT tends to have few documents to choose from.
At the push interface of JITT, the teaching agent presents links to the documents it recommends for the current stage of each active workflow.
If the JITT model for the user indicates that the user knows all the concepts for the current stage in the workflow, it continues to show the user that stage but does not display any documents.
Importantly, we have designed JITT so that the user can always change the teaching agent to select the presentation strategy they prefer.
The JITT teaching agents are based upon the Scrutable Adaptive Teaching System approach (Holden, & Kay, 1999; Holden, & Kay, 2001; Lum, Holden, & Kay, 2002).
Their workflow was deployed in a university course environment, whereas the goal of the users in JITT was to accomplish a certain business activity.
In other words, although that work involves different interface modalities, it too has forms of both the push and pull mode of information delivery available in JITT.