3.1 Established

Draft-review-before-commit checkpoint

A check-your-answers screen rendered before confirmation, where each agent-supplied answer carries its data provenance and a change link.

01 Emerging Challenges

When an agent acts on behalf of a citizen, the citizen must have the opportunity to review what the agent will do (submit a form, authorize a payment, share data, or accept a decision) before it becomes a binding action. Without this checkpoint, errors propagate into official records with no moment of human verification.

02 Assurance

A mandatory human-legible review screen before any consequential action (submitting a form, authorizing a payment, sharing data, or accepting a decision) gives the citizen a verification point. It surfaces what the agent will do, what data it used, and what it chose to include, before the action becomes binding.

03 Access

Layered disclosure: a citizen summary by default, expandable detail, and the full draft on request. Plain-language labeling of each item, with a clearly signposted change affordance beside every answer so review never assumes legal or formatting literacy.

04 Response surface
Interaction design

Check before we submit

Your assistant has prepared this. Nothing is sent until you confirm. You can change anything that isn’t locked by the evidence.

What will be filed
What you are applying for
Property tax relief (homestead exemption)
Locked
Why you qualify
This has been my primary residence since March 3, 2024. I own and occupy the home.
From when
March 3, 2024
Locked
Evidence attached
Proof of residency (1 file)
Locked

On what authority

Submitted under the single-payment and read-only document scopes you granted on June 14. The assistant is not acting on standing authority, so this confirmation is required.
The response this pattern proposes
The policy rule 'no consequential agent action is binding without a human checkpoint' becomes a summary-list review screen that names each item's data source and offers a change link before the action is committed.
05 Maturity
  1. Established Headline

    Human-in-the-loop review screens are a settled pattern across government and commercial services.

  2. Emerging

    Agent-specific review that carries data provenance for each answer is still taking shape.

06 Precedents

GOV.UK "Check your answers" pattern. The GOV.UK Design System mandates a check-your-answers page immediately before the confirmation screen for all transactional services, using a summary-list component for each group of answers with change links beside each item. It is mandatory for services meeting the UK Government Service Standard. See GOV.UK Design System — Check answers and Scottish Government Design System — Check answers.

Intuit "Review before [action]" AI pattern. Intuit's Content Design system documents an AI UX pattern — a contextual reminder near AI-generated content, e.g. "I drafted your email using your past campaigns and brand settings. Review before sending." It explicitly names the data sources the AI used, giving the user grounds for assessment. See Intuit Content Design — UX Patterns.

myTax Australia pre-lodgement review. The ATO's myTax pre-fills information from employers, banks, health funds, and share registries, then presents a review screen before lodgement so the citizen can see and amend what was pulled automatically. See ATO — Lodge your tax return online with myTax.

NHS "Check answers" pattern. The NHS digital service manual implements the same check-answers pattern adapted for health contexts. See NHS Design System — Check answers.

07 Transferability

Directly transferable but requires adaptation. When a human fills a form, the check-your-answers page reflects what they entered. When an agent fills a form, the review page must additionally surface: (a) what data the agent used, (b) what inferences or calculations it made, and (c) what it chose not to include.

The Intuit pattern is the closest existing model for this agent-specific variant because it names the data sources; the GOV.UK pattern supplies the structural template. The combination of GOV.UK's layout with Intuit's provenance labeling is the starting point.

08 Where things go wrong

The failure mode is consequential notices issued with no review checkpoint, so miscalculations reach citizens unseen. A mandatory draft-review before any notice creates a human verification point that surfaces errors before they are sent.

The worst case

Robodebt raised and issued debts through an automated process with no review checkpoint, so hundreds of thousands of incorrect notices reached citizens before a single one was examined by a human. A mandatory draft-review before any notice went out would have caught those errors while they were still drafts.
09 Sources
5 references UK · AU