Skip to main contentSkip to footer
Browse principles
Principle 7trust

Establish trust through inspectability

Users should be able to examine how a result was produced when confidence, accountability, or decision quality is important.

Key Facts

Cluster
trust
Primary risk
The system demands trust without providing a basis for it.
Related examples
6 library examples
Doctrine library
Internal doctrine reference
Why does this principle matter?

Trust is not established through assertion alone. It is established by enabling proportionate verification. Particularly in high-impact contexts, users must be able to inspect evidence, actions, and changes.

Make source material traceable.
Provide visibility into actions taken and decisions reached.
Support comparison between recommendation and result, or between draft and final output.
Maintain appropriate task history or auditability where needed.
What failure does this principle prevent?

The system demands trust without providing a basis for it.

AI as interface embellishment: A conventional product is given a text input and labelled intelligent, without any meaningful change in operational model.
Simulated autonomy: The system appears autonomous in language or presentation but cannot act with meaningful independence.
Opaque execution: Work occurs in the background without adequate status, accountability, or recoverability.
How do I apply this in practice?

The implementation library contains inspectable, runnable examples that show this principle applied in real agentic product code. Study the source paths, library choices, and runtime assumptions — not just the pattern name.

Implementation example

Intelligence: The "brain" that processes information and makes decisions using LLMs.

This component handles context understanding, instruction following, and response generation. (script · intermediate)

Inspect implementation

Implementation example

Memory: Stores and retrieves relevant information across interactions.

This component maintains conversation history and context to enable coherent multi-turn interactions. (script · intermediate)

Inspect implementation

Implementation example

Tools: Enables agents to execute specific actions in external systems.

This component provides the capability to make API calls, database updates, file operations, and other practical actions. (script · intermediate)

Inspect implementation

Related examples