Crisis communications holding statement
Draft a short, human, non-defensive holding statement for a live incident.
Higher-risk prompt — human review is required before you act on the output.
This prompt touches safeguarding, wellbeing, funding claims or public communications. Verify facts, remove personal details and check with a colleague before using the result.
When to use this prompt
Reach for this prompt when you need to draft a short, human, non-defensive holding statement for a live incident. It's designed for ceo, communications, trustee. Typically used within Communications work.
Not suitable for real-time decisions about individuals, safeguarding cases, or public claims without human sign-off.
How to use it
- 1
Gather your inputs
You'll need: known_facts, affected, commitment. - 2
Fill in the template
Copy the template below and replace every bracketed placeholder with real, local context. Keep names and safeguarding details out. - 3
Run it in your AI tool
Paste into your preferred AI assistant. Ask a follow-up if the output misses your association's tone or context. - 4
Review with the checklist
Work through the human-review checklist below before you send, publish or act on the output.
Prefer a guided flow? Adapt with the guided builder — it fills placeholders from your association profile.
Prompt template
Draft a short holding statement for {{association_name}} while we respond to a live incident.
What we can say publicly (do not invent anything else): {{known_facts}}
Who is affected: {{affected}}
Our current commitment: {{commitment}}
Tone: {{communication_tone}} — but never defensive, never distancing.
Rules:
1. Under 120 words
2. Acknowledge impact before explaining anything
3. Do not blame, minimise, or use "unfortunately"
4. Say what we're doing next and when we'll say more
5. Signpost support for anyone affected
Do not speculate. Do not invent facts.Replace bracketed placeholders with real context. Never paste identifying details about children, health or safeguarding cases.
Human review checklist
Tick each before you send or publish the output.
Why this prompt works
The "do not invent" instruction plus the ban on defensive words prevents the model from adding harm.
Was this useful?
Sign in to leave feedback and shape which prompts stay in the library.