Pattern 61
Repeated reassurance needs a different response
Notice distressing certainty loops without labelling ordinary faith questions as illness.
Concrete takeaway
Acknowledge the distress and recurrence without diagnosing OCD.
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 · Recognise recurrence | The same distressing certainty request recurs | Describe recurrence without assigning a diagnosis |
| B · No certainty promise | Absolute reassurance would repeat the loop | Warmth and qualified support must remain available |
| C · Preserve ordinary inquiry | The person has an ordinary textual question | Do not treat repetition alone as a clinical symptom |
The problem
Repeated promises of moral certainty can briefly comfort someone while encouraging another round of the same distressing question.
The pattern
Acknowledge the distress and recurrence without diagnosing OCD. Avoid new guarantees of purity, salvation or perfect certainty on each turn. Offer qualified support and a change of conversational focus if the user wants it. Do not conduct exposure therapy, impose a reassurance-withholding regimen or refuse all discussion of faith. Ordinary inquiry remains answerable. The model should not silently store a suspected diagnosis in memory.
Compare the alternatives
Notice distressing certainty loops without labelling ordinary faith questions as illness.
A · Recognise recurrence
Describe what is happening without a diagnostic label.
B · No certainty promise
Warmth can remain without another absolute guarantee.
C · Preserve ordinary inquiry
A repeated topic is not automatically a symptom.
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
Unlimited reassurance; diagnosing scrupulosity from a phrase; cold refusal; self-guided exposure instructions; a covert health label.
What to validate
Have OCD specialists review multi-turn cases alongside ordinary doubt and harmless repeated questions. Test that the assistant avoids both symptom accommodation and abandonment.
Sensitive design proposal · Specialist review required. 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.
- For Faith LeadersSpecialist guidance reviewed · Do not diagnose ordinary doubt or use a chatbot to perform exposure therapy. Guidance for human faith leaders requires careful adaptation.
- Concept of Trauma and Guidance for a Trauma-Informed ApproachPrinciples checked; full PDF access limited · An organisational approach, not a validated AI script. The full guide needs deeper review before claiming implementation fidelity.
Common scenarios and flows
- Respond to a sensitive disclosure with accountable support — Keep disclosure, present safety, user choice and service responsibility distinct.
Design principles in this decision
Editorial application of Missional by Design. These values frame review questions; they do not validate a pattern’s effectiveness.
- Reverence — What does this interaction ask of the person, and can they understand, decline, correct or leave it without penalty?
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.
Could functionality, marketing or reasonable expectations make this a companion or mental-health service? Define the human role, health claims, escalation capability and locally verified support route before selecting dialogue UI.
Start with EU and Germany, then review the relevant market:
- US · California — Enacted AI-specific law
- US · New York — Enacted AI-specific law
- US · Utah: mental-health chatbots — Enacted AI-specific law
- US · Illinois — Enacted AI-specific therapy restrictions
- US · Texas — Enacted AI-specific law; effective 1 January 2026
- US · Federal health software and data — Existing law; regulator implementation guidance
- United Kingdom — Existing law + regulator guidance; policy statement
- Australia — Existing law + regulator guidance; national policy
Use the jurisdiction decision guide to record the trigger, source version and resulting product requirement.