Incoming email
Interactive case study
See the method in action.
In my AI implementation note, I describe why reliable AI-enabled processes should be built from small, inspectable steps. This interactive example lets you see that approach in action.
SettingCustomer operations at a fictional B2B software company.
MethodExplicit rules, bounded AI tasks and human review.
Case environment
Customer operations.
Resolve account
Split and process asks
Assemble reply
Human review and send
| Ask | Type | Subtype | Requirements | Extract | Complete? | Draft | Grounding | Weigh |
|---|
The important artifact
People write the rules. The system follows them.
These are the complete tables used by the case study. Boundaries, requirements and routes are visible, reviewable and changeable without retraining anything.
Types & subtype boundaries
Only the relevant type’s list enters each classification step.
| Type | Subtype | Boundary injected |
|---|
Requirements, sources & actions
A lookup decides what happens next. No model chooses its own tools.
| Subtype | Required fields | Source | Weigh? | Action |
|---|
The only answer material
Four short, named sources.
The reply step sees one relevant snippet — never the whole knowledge base.
The operating principle
“Use judgment only where judgment is needed. Everything else should be a rule someone can inspect.”