Skip to main contentSkip to footer
Browse principles
Principle 8trust

Make hand-offs, approvals, and blockers explicit

When the system cannot proceed, the reason should be immediately visible, along with any action required from the user or another dependency.

Key Facts

Cluster
trust
Primary risk
Tasks stall silently, creating confusion and eroding confidence.
Related examples
6 library examples
Doctrine library
Internal doctrine reference
Why does this principle matter?

In agentic systems, failure frequently arises not from incorrect reasoning but from unclear responsibility. Users must know when a task is paused, why it is paused, and what will resume progress.

Surface waiting states clearly.
Explain whether the dependency is user action, system access, policy constraint, or tool failure.
Make required actions specific and minimal.
Distinguish between interruption, failure, and approval gating.
What failure does this principle prevent?

Tasks stall silently, creating confusion and eroding confidence.

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