Runtime controls & prototypes

Surfaces

Each pattern proposes a concrete control at the interaction, service, or policy level to bound what an agent can do and record what happened. Choose a territory to inspect the live surfaces.

By design level

81 surfaces

T1 Territory 7 surfaces Provenance & Intent Telling where a submission came from, and whether it states a view the user holds or one an agent generated. Nothing in a submission's text shows who wrote it, yet the agency still has to act on it.

1.1 Interaction design

Provenance Receipt

PatternCryptographic content provenance

1.2 Interaction design

Share Credentials

PatternVerifiable credentials and decentralized identity

1.3 Interaction design

Preparation Disclosure

PatternSelf-attestation and disclosure

1.4 Interaction design

Confirm Personhood

PatternProof of personhood at submission

1.5 Interaction design

Guided Intake

PatternStructured intake with process metadata

1.6 Interaction design

Composition Timeline

PatternLinking a person's input to the final text

1.7 Interaction design

Tiered Attestation

PatternThe attestation-verification gap

T2 Territory 14 surfaces Delegation & Authorization Enforcing least agency when a user grants software standing authority to act. Identity systems prove who a person is, not the minimum scope they granted an agent or how to revoke it in flight.

2.1 Interaction design

Negotiate Scope

PatternFine-grained scope negotiation

2.2 Interaction design

Manage Authority

PatternDigital power of attorney

2.3 Interaction design

Data-Access Consent

PatternConsumer data rights consent flows

2.4 Interaction design

Delegation Record

PatternConsent receipts and records

2.5 Service design

Verify Delegation

PatternDelegation registries

2.6 Service design

Bind Identity

PatternBinding an agent to a verified identity

2.7 Interaction design

Step-Up Authorization

PatternStep-up re-authorization for sensitive actions

2.8 Interaction design

Nominate Agent

PatternNominated-agent authorization

2.9 Interaction design

Access Policy

PatternUser-defined access policies

2.10 Interaction design

Protected Delegation

PatternHealthcare delegation

2.11 Interaction design

Agent Control Panel

PatternManaged agent identity

2.12 Service design

Duress Safeguard

PatternDuress-resistant delegation

2.13 Service design

Contain Agent

PatternContaining a compromised agent

2.14 Interaction design

Proffer Terms

PatternUser-set machine-readable terms

T3 Territory 11 surfaces Accountability & Audit Tracing every agent action back to a human decision-maker and halting systemic faults at runtime. Without pre-commit checkpoints and circuit breakers, a single flawed process repeats across a population before anyone sees it.

3.1 Interaction design

Draft Review

PatternReview before commit checkpoint

3.2 Interaction design

Action Receipt

PatternConfirmation receipt showing what happened

3.3 Service design

Audit Trail

PatternAudit trail with role-based views

3.4 Interaction design

Reasons for Decision

PatternReasons for decision

3.5 Service design

Dispute & Recourse

PatternRecourse and dispute resolution

3.6 Interaction design

Liability Statement

PatternShowing liability at the point of action

3.7 Interaction design

Reversibility Preview

PatternReversibility and undo

3.8 Service design

Circuit Breaker

PatternCircuit breaker for agent actions

3.9 Interaction design

Proposed-Action Notice

PatternNotice of automated action before effect

3.10 Policy design

Contest & Suspend

PatternContest before consequence

3.11 Policy design

Duty Schedule

PatternSymmetric duties on the state's agent

T4 Territory 8 surfaces Trust Calibration Helping a user judge how far to rely on a government AI agent, and giving the agency a basis to support that judgment. A user can wrongly refuse an agent that would help, or lean on one a serious case needs a human for.

4.1 Interaction design

Eligibility Check

PatternShowing confidence and uncertainty

4.2 Interaction design

Trust Mark

PatternTrust marks and certification

4.3 Interaction design

Delegation Ladder

PatternGraduated delegation

4.4 Interaction design

Transparency Moments

PatternTransparency by default

4.5 Interaction design

Automation Label

PatternCommunicating the level of automation

4.6 Interaction design

Oversight Signal

PatternSignaling human-in-the-loop oversight

4.7 Interaction design

Earned-Trust Control

PatternEarned trust and reversible delegation

4.8 Interaction design

Automation Declaration

PatternDeclared automation on outbound decisions

T5 Territory 7 surfaces Rationing & Friction Forms, queues, and deadlines rationed services for years by demanding effort no one designed in. AI agents strip that effort away, forcing a deliberate choice about which friction only excluded people and which metered need.

5.1 Policy design

Rate-Limit Meter

PatternRate limits per verified person

5.2 Interaction design

Structured Intake

PatternStructured intake that resists volume-padding

5.3 Service design

Personhood Token

PatternProof of personhood without CAPTCHAs

5.4 Service design

Participatory Budget

PatternParticipatory budgeting as an alternative to rationing

5.5 Policy design

Petition Threshold

PatternE-petition threshold design

5.6 Service design

Sludge Audit

PatternSludge audits and how they backfire

5.7 Service design

Appeals Dashboard

PatternAppeal volume and overturn rate as early warning

T6 Territory 9 surfaces Volume vs Breadth Signaling Reading the weight of opinion behind public submissions once agents file fluent, distinct-looking entries at scale. Volume and the look of variety can both be manufactured, so neither shows how widely a view is held.

6.1 Service design

Cluster Console

PatternClustering and deduplication for high-volume submissions

6.2 Service design

Submission Record

PatternProvenance and attribution for mass submissions

6.3 Interaction design

Live Opinion Map

PatternOpinion mapping by consensus and clustering

6.4 Service design

Results Dashboard

PatternWeighting distinct voices

6.5 Interaction design

Template Nudge

PatternSubmitter nudges on template matches

6.6 Interaction design

Credit Voting

PatternAlternative weighting mechanisms

6.7 Service design

Review Pipeline

PatternSubmission processing that resists prompt injection

6.8 Service design

Agent Admission

PatternVerified agent admission

6.9 Policy design

Agent Welcome

PatternDeclared agent welcome

T7 Territory 9 surfaces Representation & Equity Keeping every user able to reach a government outcome, from a consultation to a benefit, license, or appeal, as private agents come between them and government. Left alone, outcomes start to track who has the better agent.

7.1 Service design

Service Entry

PatternAgency-provided agents (a public option)

7.2 Interaction design

Voice Fidelity

PatternPreserving the person's own voice

7.3 Service design

Channel Choice

PatternNon-agent fallback channels, kept first-class

7.4 Interaction design

Accessibility Controls

PatternAccessibility baseline: WCAG and beyond

7.5 Interaction design

Language Intake

PatternPlain language and multilingual intake

7.6 Service design

Community Oversight

PatternCo-design with affected communities

7.7 Interaction design

Interest Disclosure

PatternWhose interests the platform serves

7.8 Service design

Tiered Advocacy

PatternGovernment-provided agents for high-stakes interactions

7.9 Policy design

Exclusion Assessment

PatternDigital divide and exclusion risk

T8 Territory 8 surfaces Verification & Certification Evaluating civic AI tools independently of the labs and vendors that build them. Building an authoritative-sounding agent is nearly free; verifying its reliability and backing it when it fails is not.

8.1 Service design

Trust Registry

PatternCertification marks and trust registries

8.2 Policy design

Nutrition Label

PatternNutrition labels for AI tools and datasets

8.3 Service design

Supply-Chain Status

PatternSoftware bills of materials for user-facing tools

8.4 Service design

Submission Review

PatternRisk-proportionate review of civic tools

8.5 Policy design

Risk Classification

PatternLifecycle certification for tools that advise users

8.6 Policy design

Framework Assessment

PatternFrom voluntary framework to certifiable standard

8.7 Interaction design

Grounded Answer

PatternGrounding and source attribution in AI outputs

8.8 Service design

Certification Wizard

PatternLightweight certification for the long tail

T9 Territory 8 surfaces Cross-border & Sovereignty Governing sovereign exposure across the AI supply chain when a model runs, or can be legally compelled, outside the user's jurisdiction. It decides who can reach the data and whether the service can be relied on under pressure.

9.1 Interaction design

Jurisdiction Badge

PatternJurisdiction disclosure when data is processed

9.2 Interaction design

Sovereignty Tier

PatternData-sovereignty tiers for sensitive interactions

9.3 Service design

Transparency Register

PatternAI system transparency registers

9.5 Interaction design

Transfer Basis

PatternCross-border data transfer as a design obligation

9.6 Service design

Residency Assurance

PatternSector-specific data residency

9.7 Interaction design

Model Provenance

PatternSovereign AI model selection and disclosure

9.8 Policy design

Sovereignty Stack

PatternConcentration-risk and supply-chain disclosure

9.9 Interaction design

Sovereignty Checkpoint

PatternContext-triggered disclosure