General AI

The AI system stack

Reference only. Project progress and credentials come from assessed work.

An AI product is rarely just a model. A useful system usually contains several layers.

01
Experience
What the user sees
02
Application
Context tools and controls
03
Model
Prediction engine

A complete map

LayerJob
ExperienceInterface, workflow and user feedback
ApplicationInstructions, context assembly, routing and permissions
ModelGenerates or predicts from an input
DataSource documents, records, examples and metadata
ToolsExternal capabilities the application may call
ControlsIdentity, approvals, logging, limits and recovery
EvaluationTests whether the system meets its intended standard

Changing a model can change quality, speed and cost. It does not automatically repair poor data, vague instructions or excessive permissions.

Vocabulary habit

When someone says "the AI knows our policies", translate it into system terms: the application may retrieve policy documents and place selected passages into the model context. The policy source remains outside the model.

The AI system stack | Mariete Academy