Adres
Playground/ docs
AIAI Design

Architecture & Trust

Autonomy levels, integration architecture, and what builds or destroys trust in AI products.

Architecture & Trust

Autonomy levels — a design decision, not an implementation detail

Autonomy level determines how much the user is in the loop. It should match the reversibility of actions and the trust earned through product experience. Design for Level 1. Earn Level 4+.

LevelNameWhat AI doesWhat human doesRequired whenReview UX
L0No AINothingEverythingScope is deterministicNone
L1SuggestProposes optionsDecides and executesAlways for novel AI introductionsPrompt/suggestion UI
L2ConfirmExecutes with step approvalConfirms each stepConsequential, reversible actionsStep-by-step checkpoint
L3DelegateExecutes at checkpoint gatesReviews at defined milestonesComplex tasks, trusted domainMilestone review UI
L4AutomateExecutes, notifies afterMonitors and can interveneRoutine, reversible, high-volumeAction log + undo
L5AutonomousExecutes without notificationAudits retrospectivelyOnly with full reversibility guaranteeAudit trail only

Integration architecture — how AI fits into a product

Visibility

Invisible AI

AI operates without surface-level disclosure. Risk: hidden manipulation. Use only when action is trivially reversible and stakes are zero.

Explicit AI

AI is always labelled and its outputs are clearly attributed. Required for all consequential AI.

Timing

Synchronous AI

User waits for AI output. Best for interactive, real-time flows. Max acceptable latency: ~2s before UX degrades.

Asynchronous AI

User continues working while AI processes in background. Best for long-running tasks, batch operations.

Assistant vs Collaborator vs Agent

AssistantCollaboratorAgent
InitiationUserBidirectionalAI
Scope1 actionSession-wideGoal-wide
MemoryNoneSessionFull context
Write accessNeverLimitedFull + gates
FailureUser retriesUser correctsAuto-recovery
AuditOutput onlyProcess + outFull trail

Trust & Safety — what builds it, what destroys it

What builds trust

Transparency about what AI did and why — every time

Consistent, predictable behaviour across sessions

Accurate confidence calibration — AI knows what it doesn't know

Easy, fast, prominent correction and undo mechanisms

Visible review loop for high-stakes actions

AI that admits uncertainty rather than guessing confidently

Source attribution for factual claims

Clear scope boundaries — users know what AI can and can't touch

Behaviour that matches what was promised during onboarding

What destroys trust

AI making errors without acknowledgment or recovery

No way to undo AI actions — especially consequential ones

Uncertain information presented with false confidence

Surprise automation — user didn't know AI would act

AI behaviour that feels like surveillance, not assistance

Sycophancy — AI always agrees with users regardless of facts

AI ignoring user corrections or failing to learn from them

Invisible AI — users don't know they're interacting with it

Over-promising capability, then consistently under-delivering