# Support Request Builder

# Copy/paste prompt — Support Request Builder

> Paste everything below into your AI tool.

---

Help me draft one support request — words only, nothing is sent.

I'll give you:

- **The loop I'm holding** — the recurring thing I keep tracking
- **What I'd want another person to own or do** — own the loop, or help once
- **What agreement or confirmation I'd need**

Draft **one** short, specific request I could adapt.

Rules for you:

- Distinguish helping once from owning the loop — say which this draft asks for.
- A request is NOT a completed handoff. Do not say I've released anything — that only happens when a real person has actually agreed to hold it.
- If no one is available to ask, it isn't safe to ask, or I'm not ready — say that's a complete answer and stop there.
- If asking could increase danger, retaliation, coercion, or control — do not produce a script; point me toward trusted or specialized support instead.
- One draft. Short. End with permission to stop.

Capacity right now — optional:
[leave blank / I don't know / prefer not to label / declared NSIF state]

If I name a Capacity State, adapt your response: language, length, number of choices, task complexity, and interaction length.
If I leave this blank or say "I don't know," default to the lowest-load response — the shortest output, one choice at most.
Never infer or declare my Capacity State.
If I say I have no capacity for this right now — or describe needing nothing — do not continue a normal exercise. A minimal acknowledgment, a human-support option if relevant, and stop.

Rules: Acknowledge briefly first, before sorting or analyzing. Work with fragments — do not require more disclosure than I give. Do only what I asked; do not expand scope. Do not diagnose me, interpret my nervous system, evaluate my motherhood, or act as a therapist.

You cannot see me, my child, my home, or my environment. Do NOT determine or evaluate:

- child safety, supervision, feeding adequacy, medical or medication needs, developmental needs, or whether required child care can be skipped
- legal, custody, parenting, caregiving, workplace, school, or financial obligations
- whether any consequential responsibility can wait or disappear

If any of these are unclear, do not decide for me — use "Needs another adult / professional / official source."

If I describe immediate danger, abuse or neglect concerns, a child or adult safety issue, or a medical emergency — stop this exercise and direct me to appropriate emergency, crisis, or professional support.

If asking for help, setting a boundary, or confronting someone could increase danger, retaliation, coercion, or control — do not produce a confrontation or request script. Point me toward a trusted or specialized support pathway instead.

One cycle only — when done, tell me I can stop here; do not offer another task or ask "want me to...". I do not have to feel better for this to count.

Privacy: Do not paste passwords, 2FA codes, account numbers, full medical/legal/custody records, confidential work or school data, children's identifying or private records, or another person's sensitive information without permission. Use general labels where possible. My AI provider's storage, retention, training, and privacy settings still apply.

The loop and what I'd want — messy is fine:

```
[PASTE HERE]
```

---

**Stop whenever enough.** A draft you never send still counts.