0.7.15 Modeling AI and Human Judgment With a UML Activity Diagram

AI Use Is a Process

AI interaction can be modeled as a sequence of actions and decisions.

A useful process includes both:

  • the AI system;
  • the human user.

The AI generates an output.

The human evaluates and decides what happens next.

A UML activity diagram can make those responsibilities visible.

Use Activity Partitions for Responsibility

You have already used activity partitions, or swimlanes, for browser/server interactions.

The same idea can separate:

Activity diagram showing HUMAN, then Start, then Identify task, then Decide what information is appropriate to share, then Create prompt.
HUMAN.
  • New
  • Changed
  • Removed

This prevents the diagram from implying that responsible AI use begins only after the output arrives.

Hand the Prompt to the AI System

The flow crosses into the AI lane:

Activity diagram showing HUMAN AI SYSTEM, then Create prompt Receive input, then Generate output, then Receive output Return output.
HUMANAISYSTEM.
  • New
  • Changed
  • Removed

The handoff shows the responsibility change.

The human supplies input.

The AI system generates the response.

Evaluation Returns to the Human

After receiving the response, the human evaluates:

  • relevance;
  • accuracy concerns;
  • credibility;
  • missing context;
  • bias;
  • privacy or rule issues.

The AI does not make the final decision about whether its own response should be used.

Add a Verification Decision

A useful decision is:

Conceptually:

Activity diagram showing Evaluate response, then Important claim needs evidence?, then [yes] Verify with authoritative source, then [no] Continue decision.
EvaluateResponse.
  • New
  • Changed
  • Removed

The verification action belongs in the human process.

The person selects and interprets the evidence.

Model Accept, Revise, Verify, or Reject

A simplified decision section could be:

Activity diagram showing Evaluate output, then Need verification?, then [yes] Verify claim Re-evaluate, then [no], then Usable as-is?, then [yes] Accept.
EvaluateOutput.
  • New
  • Changed
  • Removed

The exact diagram can vary.

The important requirement is that the human judgment remains visible.

Revision Can Create Another AI Interaction

If the human chooses to revise the prompt, the flow may return to the AI system.

For example:

Activity diagram showing Revise prompt, then AI receives new prompt, then AI generates new output, then Human evaluates again.
RevisePrompt.
  • New
  • Changed
  • Removed

This forms an iteration loop.

The loop should not imply:

Each new output still needs evaluation.

Verification May Use a Source Outside the AI System

If the AI makes a factual claim, the human may consult an authoritative source.

The diagram can include an action such as:

Verify claim with authoritative source

You do not need to create a separate swimlane for every possible website or document unless the purpose of the model requires it.

Keep the current diagram focused on AI and human responsibility.

End With a Human Decision

A strong model should end with an action owned by the human.

For example:

Use revised output

or:

Reject output

Then:

End

This preserves the central principle:

AI generates; the human decides.

Read the Diagram as a Responsibility Story

A complete explanation might be:

If the diagram communicates that story clearly, it is representing responsible AI use rather than only the technical prompt/response exchange.