What to Expect if You Take Part
This page explains, in plain language, how the chatbot will work with you over the study period: what you choose at the start, what kinds of conversations it supports, and how safety is handled.
1. Choosing how to work
At the beginning you choose a lead companion and basic settings. You can change your mind later.
- Choose a lead persona: Charlie (steady, direct, peer-like) or Mishka (warm, reflective).
- Choose your main language for text (for example, English or Ukrainian).
- Decide whether you want to invite the optional Internal Council perspectives (Spirit Guide, Philosopher, Researcher) at times.
You stay in control. The chatbot adapts to your preferences over time, but you can always change persona, language, or how "deep" you want conversations to go.
2. What the chatbot will and will not do
The assistant is designed to support early contact, not to replace human care or crisis services.
- It will: check in regularly, reflect back patterns, suggest small grounding or planning steps, and help you notice change over time.
- It will not: make a diagnosis, pressure you into talking about trauma details, or give commands about what you must do.
- It will prompt you with options rather than demands, and respect "I do not want to talk about this now".
You can also use the chatbot for everyday topics (sleep, routines, food, training plans, future goals) when that feels more useful.
3. How safety and escalation work
Your language is monitored for signs of high distress or risk. When certain patterns appear, the assistant responds more carefully.
- If you sound under strain but still in control, it may slow the pace, suggest grounding, or gently invite human support.
- If you mention self harm or feeling out of control, it will avoid detailed questioning and show you clear crisis options.
- It keeps a simple internal banding (Green, Amber, Red) to guide how cautious it should be.
You can always ask "why are you suggesting this now?" and the assistant will explain its reasoning in plain language.
4. Data, consent, and stepping away
This is a research prototype. Any use in a real study would follow a clear consent form and ethics approval.
- You would be told exactly what is stored, for how long, and who can see it.
- You would be able to stop taking part at any time without having to give a reason.
- Where possible, your data would be minimised, de-identified, and used for research purposes only.
For this prototype demo, no real personal data is collected or stored.
5. Optional deeper modes (psychedelic-informed arm)
Later in the journey, if things feel stable enough, you may be offered the option to enter a more reflective mode for short periods.
- Containment: Spirit Guide style grounding and values reminders.
- Exploration: Philosopher style questions about meaning and dilemmas.
- Integration: Researcher style summarising of "what helped" and small next steps.
This is modelled on some of the structure of psychedelic-assisted therapy (set, setting, integration) but does not involve any drugs, only dialogical mode shifts.