Practical AI for
enterprise architects
One company. Two possible first transitions.
Your prompt enters the harness.
The model chooses what to load, one step at a time.
Every token has a price.
Context window
What would you change in this skill?
Session 1 · 17 minutes
Improve the skill, then test what changed.
“We’ll know it works when ; we’ll check this by .”
Session 2
Simulate the impact of your recommendation.
An MCP server makes tools available.
One harness. Multiple MCP servers.
MCP is more than tools.
The same agent loop · now with MCP tools
The model chooses when to use a tool.
Does everything over MCP use tokens?
Input tokensWhen included in the model request.
Output tokensThe model generates the request.
Input tokensOnly the content passed into model context.
Outside the modelNo model tokens unless content is sent to a model.
Session 2 · Group work
Connect. Simulate. Share what you discover.
Connect your harness
Add https://app.caplo.ai/mcp to your client. Sign in and select the workshop workspace. Find the ArchiSurance applications and relationships.
Draft the impact
Use recommendation.md to model the change in your group’s own Shared draft, in the shared repository. Inspect affected applications and dependencies.
Share your findings
Show the proposed change. What did the repository reveal that your original recommendation missed?
The architect’s contribution
Method. Evidence. Trade-off. Decision.
The AI can make the work faster and more repeatable. The architect sets the evidence threshold, handles uncertainty and accepts the change.
SkillA reusable way of working, loaded only when relevant.
MCPA standard connection to tools and context.
DraftA proposed architecture state that people can inspect.
Continue the conversation
Let’s stay in touch.
Bram Verswalm
Scan to connect on LinkedIn