aiExpert In Practice – #2 – Archimate 3

Source diagram

The source of this model is the Archimate example which is delivered in the Sparx ‘EAExample’ model, which is installed when you install EA.

This diagram can be found at: Example Model.Enterprise Architecture.Architectural Frameworks.ArchiMate3.Example 18 – Stakeholder, Driver and Assessment, in the EA v17 version of EAExample.

The purpose of this document is to describe what the results were when parts of this model were analyzed by the aiExpert ‘Archimate Motivation Model’ query, which is used to examine the ‘purple layer’ of an Archimate model.

Please note that this is using the out-of-the-box function of aiExpert, with no tailoring of the prompts to suit the domain.

Model Diagram 'Example 18 - Stakeholder, Driver and Assessment'

The diagram which aiExpert analyzed was “Example 18 – Stakeholder, Driver and Assessment” which is an example of an Archimate ‘Motivation layer’ model.

Inputs

We chose the ‘Archimate Motivation Model’ query for this analysis, which collects all the data about each Archimate element, and all their connectors, and submits this to the LLM with the prompts:

System instructions: “You are an expert in the style and structure of Archimate 3 Motivation layer models”

Rules: “

Here are some parts of an Archimate 3 Motivation model.
Use these authoritative sources for best-practice rules and guidance:
– The Open Group ArchiMate® 3.2 Specification (Motivation layer semantics, allowed relationships).
– The Open Group ArchiMate® Practitioners’ Guide (recommended usage patterns).
– The TOGAF® Standard, Business Architecture guidance (linking drivers, goals, principles, and requirements).
– Wierda, G. *Mastering ArchiMate* (practical modeling style and pitfalls to avoid).
– Practitioner blogs/white papers from the ArchiMate Forum (Open Group) for clarity and good practice.

When checking a model:
– Ensure all elements and relationships conform to the ArchiMate 3.2 metamodel.
– Flag common misuse highlighted in the Practitioners’ Guide and *Mastering ArchiMate*.
– Provide short, clear feedback. Where relevant, cite which source (e.g. “ArchiMate Spec”, “Practitioners’ Guide”) the rule comes from.
– Do not invent new rules beyond these sources.
When you respond, grade the severity from 1 – a minor issue, to 5 – a serious problem.
Always include the ID of each element with any feedback”

LLM used: gpt-5-mini

Data collector: ConnectorDetail

Important note:

We present the details of the Ai analysis largely without comment. This is not our model: we don’t understand the domain, so we are not in a position to say whether the feedback from the LLM is good or bad, useful or useless.  What we can say is whether the feedback might be useful, or whether it seems silly.

In the ‘suggested fix’ information which is returned by the AI, we highlight in italics the part of the input message to which the feedback refers.