Control

Control

Let the human set the rules

What it means

Humans guide how agents operate by setting boundaries, preferences, and intent. Rather than making assumptions, agents respond to this direction with flexibility. Control doesn’t mean limiting autonomy, it means aligning it with human goals.

Why this matters

People are more likely to trust and engage with agents when they understand how decisions are made, and can shape them. Giving users control over behaviors, permissions, and preferences makes the system feel collaborative and intentional, rather than unpredictable.

Related patterns

Scope & boundaries
Users define operational limits for AI behavior. The agent operates within these boundaries, avoiding unintended actions.
Related pattern
Instruction / Scope
Related Pattern
1

Instruction mode

Users define interaction boundaries by selecting input modes, guiding the agent to operate safely within intended, user-controlled scopes.

2

Task specific boundaries

Specific checkboxes define what the AI is allowed to change (e.g., title edits) and what it must avoid. These helps in defining clear behavioral constraints.

Customization of autonomy
Users control the spectrum of autonomy, from passive suggestions to full automation based on their comfort and context.
Related pattern
Authority Sliders
Customization of Autonomy
1

Monitoring

Agent only observes, all decisions are manually approved. This is useful for audit, analysis, or low-trust mode.

2

Guided

Agent suggests actions and it can analyze and simulate rerouting or bandwidth decisions. Very similar to co-pilot.

3

Full control

Agent manages the system autonomously and has full control to make decisions.

Permission & confirmation gates
Explicit checkpoints require human approval before proceeding. Safeguards critical operations through shared decision-making.
Related pattern
Kill switch and preview modes
Permission & Confirmation Gates
1

Immediate agent shutdown

A prominent “Disable Agent” toggle gives users a fast, irreversible way to halt all agent activity. This supports emergency intervention and restores user authority instantly.

2

Visible control settings

The system shows settings upfront allowing the user to assess whether to make decisions based on risks and live situations.

How to implement

Make automation opt-in, never assume users want it
Let users override any system decision, anytime
Show what rules are active and how they're working
Make it easy to change and adjust settings

Common pitfalls

Over-reliance on implicit controls
Assuming users understand what the agent is doing without clear communication
Boundary creep
Agents gradually take on more than intended without safeguards or oversight
Ambiguous authority
It is unclear if the agent or the human is responsible for the task, especially in case of failure states
Hidden behavior
The agent performs actions without surfacing intent or outcomes to the user