Dialogical Chatbot
Frontier Psychology research prototype

Study Timeline & Proposed Contact Schedule

This page describes how we intend to test and refine the chatbot over time. The schedule shown here is a proposed structure for research and supervision — it is not a prescription for how an individual ‘should’ recover. The aim is to evaluate how the assistant adapts its stance, pacing, and safety responses in a transparent, user-controlled way.

Study roadmapProposed cadenceSafety-first
Start Onboarding Monitoring Demo

1) Study roadmap (how this will evolve)

We treat this as a staged research build: first proving safe dialogue and controllable escalation, then trialling cadence, then evaluating feasibility with partners. The ‘timeline’ is therefore two things: (a) a development plan for the study, and (b) a proposed contact rhythm inside the future system.

Stage A — Prototype & supervision demos (now)

  • Prove: persona onboarding, safe language, user control, escalation ladders.
  • Create: Monitoring & Escalation Demo page as a transparent ‘glass box’.
  • Refine: wording for simplicity (health literacy), bilingual tone, and humane pacing.

Stage B — Feasibility pilot (partner-led)

  • Test: usability, acceptability, safety comprehension, and engagement.
  • Evaluate: whether the assistant maintains a safe trajectory (containment → regulation → gentle exploration).
  • Document: where human oversight is required and what ‘handover’ looks like in practice.

Stage C — Expanded study / full evaluation

  • Compare: different cadence choices and persona configurations.
  • Assess: whether language-based monitoring improves safety and reduces drop-off.
  • Produce: publishable write-up and partner-facing implementation plan.

2) Contact schedule concept (user-paced)

The TRiM-inspired rhythm is a scaffold, not a cage. Some users may want a short, intensive run (days), while others may prefer a slower pattern (weeks). The system should make pace explicit and negotiable, and it should never treat oscillation as failure. Reflection on traumatic experience should be invited only when the interaction suggests enough steadiness, and when psychoeducation has helped the user understand what reflective work is for.

Three-layer structure

Layer 1 — Open support (always available)

You can drop in at any time for grounding, routines, planning, or simply company. Not every conversation is about trauma.

Layer 2 — Optional structured check-ins (proposed cadence)

Light-touch check-ins help the assistant adjust stance and safety responses over time (pace, warmth, directness, grounding). They are not ‘scores’ of you; they are signals used to respond safely.

Layer 3 — Memory reorientation (carefully timed, always optional)

When the conversation shows enough stability, and after brief psychoeducation about trauma memory, the assistant can gently help the user reflect on the experience in the least overwhelming way available: sequencing fragments, distinguishing then from now, identifying what feels unfinished, and choosing whether to stay with reflection, pause, or return to regulation.

Important: signals can swing. A “worse day” does not mean failure. The point is to help the assistant respond with the right stance (pace, warmth, grounding, containment), and to offer human routes when needed.

Memory reorientation: how reflection should be guided

This layer is not about pushing disclosure. The idea is to use the interaction itself, plus simple psychoeducation, to judge when reflective work is appropriate and what form it should take. Some users may only need grounding and orientation; others may be ready for a small amount of structured reflection.

  • Start with psychoeducation: explain in plain language that trauma memory can arrive in fragments, body alarms, images, or loops, and that reflection should stay manageable.
  • Use the interaction as a guide: if language is disorganised, highly activated, or shutdown, stay with containment and regulation rather than moving into memory work.
  • Orient memory before interpreting it: help the user separate past from present, place events in sequence, and notice what is known, uncertain, or still confusing.
  • Offer the least intense reflective route first: brief meaning-making, values questions, or simple narrative stitching before any deeper exploration.
  • Keep exits visible: return to grounding, pause the topic, or hand over to human support whenever reflection begins to destabilise rather than clarify.

3) What we are testing (and what we are not)

This prototype prioritises presence, safety, and transparency. Any structured elements are used to test the assistant’s behaviour — not to diagnose a person or quantify recovery.

We are testing

  • Whether the assistant maintains a safe therapeutic direction (containment → regulation → gentle exploration).
  • Whether language-based monitoring can detect rising distress and adapt stance appropriately.
  • Whether escalation pathways are understandable, localised, and user-controllable.
  • Whether personas and Council invitations improve engagement without increasing risk.

We are not testing

  • A clinical outcome tool or diagnostic system.
  • A replacement for therapists, TRiM practitioners, or crisis services.
  • A rigid programme that users must follow.

4) Safety, consent, and human oversight

Safety is a first-class design constraint. Monitoring is explained and consented. The user can pause, change topic, or stop at any time. Escalation is signposting + human routing — never false certainty.

  • No pressure into trauma detail or exposure.
  • Clear escalation ladder with locale-specific crisis options (demo placeholders are acceptable).
  • User can view/edit/erase memory (when implemented).
  • Research mode is opt-in; consent can be withdrawn.
Safety-first Design Trajectory-first Design