Pattern 16
Conversation can produce a reading artifact
Move sustained work into an editable document without losing its origin.
Concrete takeaway
Offer an explicit transition into a document or workspace.
Choose an approach
These are editorial decision conditions to validate. Some alternatives are successive states or can be combined; they are not always exclusive choices.
| Alternative | Use when | Tradeoff or requirement |
|---|---|---|
| A · Draft in conversation | The output is a short conversational draft | Editing inside chat may be limited |
| B · Editable document | The output needs sustained revision | A document adds another surface and return state |
| C · Review a suggestion | AI suggests an edit to existing work | Review and rejection must remain possible |
The problem
A long study note or plan becomes hard to revise when it remains buried inside a sequence of chat bubbles.
The pattern
Offer an explicit transition into a document or workspace. Preserve the originating question and references. Keep the user’s writing distinct from AI suggestions, with review before replacing or saving text.
Compare the alternatives
Move sustained work into an editable document without losing its origin.
A · Draft in conversation
Creating an artifact is a deliberate transition.
B · Editable document
The reading artifact has its own structure.
C · Review a suggestion
Proposed changes do not overwrite the user’s voice.
Original wireframe proposals · No live controls · Grey rows represent schematic text, not loading states · Labelled placeholders are not Scripture quotations
Download this wireframe as SVGFailure modes
Silently rewriting a personal reflection; automatic publication; a generated document without source links or a route back to the conversation.
What to validate
Can people edit, compare changes and return to the original question? Does rejecting a suggestion leave their own wording intact?
Research-informed design proposal. These visual alternatives have not been tested with users in this atlas. Source findings, documented behaviour and this proposed adaptation are different kinds of evidence.
Sources and adaptation
This card is an original design synthesis. The following sources inform its content distinctions, interaction approach or review requirements; they do not validate the whole pattern.
- AI UX PlaygroundCatalogue and selected detail pages reviewed · Selected relevant entries reviewed; the entire catalogue was not audited. Its FAQ currently describes 150 patterns in 11 categories.
- AI UX PatternsPublic sample and catalogue framing reviewed · The pattern-composition example is a design reference, not a validation of the proposed faith-specific variants.
- Pattern CatalogueCatalogue entries and descriptions reviewed · A broad observational design catalogue rather than an exclusively AI or faith resource.
Common scenarios and flows
- Prepare and participate in an AI-assisted practice — Use bounded adaptation while keeping Scripture, authorship and user choice inspectable.
- Prepare teaching with accountable evidence — Build an explanation that another person can inspect, without outsourcing interpretive responsibility.
Examples in use
Attributed app evidence with dates and review limits. A screenshot illustrates an implementation; it does not establish that the proposal works for every audience.
Design principles in this decision
Editorial application of Missional by Design. These values frame review questions; they do not validate a pattern’s effectiveness.
- Bridge — What does this experience enable beyond the session, and is the next step voluntary, accessible and safe?
Compare alternatives using the task and evidence above. Record competing needs instead of treating a principle as an automatic verdict.
Regional applicability
Design review questions · 5 October 2026. These prompts identify possible triggers; they do not classify this pattern or every faith app as a regulated service.
Does generated text, audio or media leave the app? Decide which origin information remains understandable in playback, download and sharing, and which file metadata the applicable role requires.
Start with EU and Germany, then review the relevant market:
- US · Utah: generated-media provenance — Enacted; relevant duties scheduled for 2027
- China — Binding AI-content labelling measures; effective 1 September 2025
- South Korea — AI Basic Act in force; announced enforcement grace period
Use the jurisdiction decision guide to record the trigger, source version and resulting product requirement.