The AI Taxonomy.
Terms  /  System Transparency  /  Explainable Delegation
06 · System Transparency

Explainable Delegation

The agent not only does the work but can explain what it did and why in terms the user understands.

Explainable Delegation bridges the gap between automation and understanding. It's not enough for the agent to complete the task — the user should be able to understand the work well enough to evaluate it, learn from it, and modify it if needed. This is especially important for Informed Delegation: you can't delegate informedly if you can't understand the work that comes back. Explainable Delegation also prevents Ownership Erosion by keeping the user intellectually engaged with the output.

Example
An agent completes a database optimization task and reports: "I added an index on `orders.customer_id` because your most frequent query filters on this column (ran 14,000 times yesterday). The index will use approximately 12MB of storage and improve that query's response time from ~800ms to ~5ms. I didn't index `orders.created_at` even though it appears in WHERE clauses, because those queries also use `customer_id` and the composite index would add 28MB with only marginal improvement. If query patterns change, we should revisit." The user understands the decision and can evaluate it.

More in System Transparency

System Opacity

The inability to see what an AI system knows, why it made a decision, or what it did. The default state of most AI tools today.

Decision Fog

The user can see the output but not the reasoning, trade-offs, or alternatives the model considered.

Black Box Agency

An agent that acts on your behalf but won't show its work. You get results with no audit trail.

Invisible State

The system has internal state that affects behavior but is not exposed to the user.

Accountability Gap

No one — human or system — can explain why a specific output was produced.

Reasoning Visibility

The user can inspect the model's chain of thought, assumptions, and decision points.

Decision Traceability

Every output can be traced back through the reasoning, context, and data that produced it.

Open State

The system's internal state is visible and inspectable at any time. The opposite of Invisible State.