Make a tense announcement easier to hear.
The hard part of a tense announcement is often the meaning people attach to it. Understand what different groups are likely to hear, then say the difficult thing clearly and give them something solid to work with.
Try it now
Copy the prompt into your AI tool of choice, then answer its questions as they come.
Paste it into any AI chat to start. For most people, this is all you need.
Everything on this page in one paste: the prompt plus the full plan, every step and what to check. Use it for longer moves, to plan ahead, to share with a colleague, or if your AI can't open links.
How it goes
What the AI will do
- Investigates the decision and affected groups through relevant correspondence, meetings, documents, and company records.
- Uses separate, evidence-informed audience perspectives to review and improve the announcement.
What to have ready
- A draft, rough description, or link to the decision and the people affected.
- Access to relevant records where available; the AI helps find usable alternatives.
Where you come in
- Clarify consequential gaps in what is decided and what can be promised.
- Confirm the intended audience and review the revised announcement.
What you'll get
A usable announcement and concise notes on likely audience questions, grounded in the records available. If audience evidence is limited, the notes identify which reactions are hypotheses.
You're done when
You have a revised announcement whose facts and commitments match the available record, plus the important audience questions and any specific decisions still needed before use.
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result. ### Start with the activity and the user's context Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear. Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them. ### Check the capabilities needed for this work Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit. When useful access is missing: - Explain what you cannot reach and how that material would help. - Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot. - If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response. - Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available. ### Ask focused questions and respect the answers Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful. Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements. ### Keep evidence and independent contributions distinct Distinguish evidence, inference, and missing information. Check your work against the source material. Use independent agents when your system actually supports delegation and independent investigation or review would improve the work: - Give each agent a bounded brief and the context appropriate to its role. - Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations. - Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately. ### Produce, check, and revise the result Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them. Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result. Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized. ### Establish what needs to be announced Help me make a tense announcement easier to hear while communicating the substance accurately. Start with any draft or description I supplied. Establish the decision, who needs to hear it, the communication channel, and what people need to understand or do afterward. If there is no announcement material, ask for a rough description; do not require a polished brief. Inspect and try relevant available connections before asking me to reconstruct the history. Search emails and chats about the decision, calendar invitations and linked meeting transcripts, decision documents, project plans, and relevant company data. Use names, dates, projects, and phrases in the material to find prior promises, disagreements, changing decisions, implementation details, and the reasons behind the change. Follow references to earlier versions where they materially affect what can honestly be said. Keep a compact record of sources, dates, and consequential gaps. If access is missing, investigate connection or export routes and help me supply the specific material needed. Work from available material when possible; a thin record supports a provisional communication review, not confident claims about employees' attitudes. ### Establish the decision and the audiences Separate what has been decided, what remains open, what is uncertain, and what I am authorized to promise. Identify groups affected differently: for example, people losing familiar responsibilities, managers who must implement the change, and colleagues who depend on their work. Use actual attendee lists, project roles, correspondence, and meeting contributions to establish those groups and their expressed concerns. Show me the central unresolved issue, if any, and ask a focused question. Wait before wording that depends on its answer. Confirm commitments you propose on my behalf. Where two approaches have a meaningful consequence—such as one common announcement versus a common announcement with a manager briefing—explain the difference and recommend one. Do not turn this into a questionnaire if the supplied context already settles it. ### Read the change from different positions Use separate audience agents where available and useful. Give each a bounded brief containing the relevant decision evidence, source references, its audience's actual circumstances, known concerns, and uncertainties. Ask it to identify: - What this group has reason to fear, welcome, or question. - Which parts of the decision affect its work or standing. - What it needs explained, and what reassurance the evidence does not support. - Plausible alternative readings, marked as simulations rather than actual reactions. Keep their initial assessments independent before synthesis. Divide a large record by audience or issue, keep a coverage record, and use successive waves when capacity is limited. Do not give every agent the entire company history. Without agents, use manageable passes or fresh sessions with explicit evidence handoffs; disclose when perspectives share context and lack independent review. ### Draft an announcement people can use Reconcile the audience findings against the decision evidence. Write the actual announcement in the intended format and my appropriate voice. State the decision plainly, explain why it is happening, acknowledge concrete effects, distinguish settled details from open questions, and make the next action or next update specific where the record supports it. Address legitimate concerns without pretending everyone benefits or supplying emotional reactions on people's behalf. Preserve difficult facts. Replace vague reassurance with an explanation, an established commitment, or an honest statement of what is still unknown. Keep internal analysis and speculation out of the announcement itself. ### Review the wording and deliver Return the actual draft to the audience reviewers with their source packets. Ask them to point to specific lines that could mislead, obscure an impact, or leave a foreseeable question unanswered. Reconcile their findings; a simulated objection is a reason to inspect the wording, not proof that the audience will react that way. Check dates, decisions, promises, and instructions against sources and revise. Deliver the finished announcement as an editable document when supported, otherwise as complete ready-to-use text. Include brief separate notes on important audience questions, the evidence behind consequential wording choices, and any unresolved details needing my decision. If missing information prevents a final announcement, clearly mark the draft and its exact unfinished commitments rather than claiming it is ready. Stop after this preparation; do not send or publish the announcement. These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
View full AI instructions
Make a tense announcement easier to hear.
What the AI will do
- Investigates the decision and affected groups through relevant correspondence, meetings, documents, and company records.
- Uses separate, evidence-informed audience perspectives to review and improve the announcement.
What you can provide
- A draft, rough description, or link to the decision and the people affected.
- Access to relevant records where available; the AI helps find usable alternatives.
Where you'll take part
- Clarify consequential gaps in what is decided and what can be promised.
- Confirm the intended audience and review the revised announcement.
What you'll get
A usable announcement and concise notes on likely audience questions, grounded in the records available. If audience evidence is limited, the notes identify which reactions are hypotheses.
Activity context
The hard part of a tense announcement is often the meaning people attach to it. Understand what different groups are likely to hear, then say the difficult thing clearly and give them something solid to work with.
For the user
Bring the announcement or describe the decision in rough terms. The AI will investigate the context, establish what different groups have reason to care about, and draft and review the wording. You will clarify any unresolved decisions or commitments before they become part of the announcement.
Guidance for the AI
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.
Start with the activity and the user's context
Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.
Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.
Check the capabilities needed for this work
Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.
When useful access is missing:
- Explain what you cannot reach and how that material would help.
- Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.
- If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.
- Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.
Ask focused questions and respect the answers
Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.
Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.
Keep evidence and independent contributions distinct
Distinguish evidence, inference, and missing information. Check your work against the source material.
Use independent agents when your system actually supports delegation and independent investigation or review would improve the work:
- Give each agent a bounded brief and the context appropriate to its role.
- Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.
- Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.
Produce, check, and revise the result
Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.
Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.
Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.
Your AI prompt
Establish what needs to be announced
Help me make a tense announcement easier to hear while communicating the substance accurately. Start with any draft or description I supplied. Establish the decision, who needs to hear it, the communication channel, and what people need to understand or do afterward. If there is no announcement material, ask for a rough description; do not require a polished brief.
Inspect and try relevant available connections before asking me to reconstruct the history. Search emails and chats about the decision, calendar invitations and linked meeting transcripts, decision documents, project plans, and relevant company data. Use names, dates, projects, and phrases in the material to find prior promises, disagreements, changing decisions, implementation details, and the reasons behind the change. Follow references to earlier versions where they materially affect what can honestly be said.
Keep a compact record of sources, dates, and consequential gaps. If access is missing, investigate connection or export routes and help me supply the specific material needed. Work from available material when possible; a thin record supports a provisional communication review, not confident claims about employees' attitudes.
Establish the decision and the audiences
Separate what has been decided, what remains open, what is uncertain, and what I am authorized to promise. Identify groups affected differently: for example, people losing familiar responsibilities, managers who must implement the change, and colleagues who depend on their work. Use actual attendee lists, project roles, correspondence, and meeting contributions to establish those groups and their expressed concerns.
Show me the central unresolved issue, if any, and ask a focused question. Wait before wording that depends on its answer. Confirm commitments you propose on my behalf. Where two approaches have a meaningful consequence—such as one common announcement versus a common announcement with a manager briefing—explain the difference and recommend one. Do not turn this into a questionnaire if the supplied context already settles it.
Read the change from different positions
Use separate audience agents where available and useful. Give each a bounded brief containing the relevant decision evidence, source references, its audience's actual circumstances, known concerns, and uncertainties. Ask it to identify:
- What this group has reason to fear, welcome, or question.
- Which parts of the decision affect its work or standing.
- What it needs explained, and what reassurance the evidence does not support.
- Plausible alternative readings, marked as simulations rather than actual reactions.
Keep their initial assessments independent before synthesis. Divide a large record by audience or issue, keep a coverage record, and use successive waves when capacity is limited. Do not give every agent the entire company history. Without agents, use manageable passes or fresh sessions with explicit evidence handoffs; disclose when perspectives share context and lack independent review.
Draft an announcement people can use
Reconcile the audience findings against the decision evidence. Write the actual announcement in the intended format and my appropriate voice. State the decision plainly, explain why it is happening, acknowledge concrete effects, distinguish settled details from open questions, and make the next action or next update specific where the record supports it.
Address legitimate concerns without pretending everyone benefits or supplying emotional reactions on people's behalf. Preserve difficult facts. Replace vague reassurance with an explanation, an established commitment, or an honest statement of what is still unknown. Keep internal analysis and speculation out of the announcement itself.
Review the wording and deliver
Return the actual draft to the audience reviewers with their source packets. Ask them to point to specific lines that could mislead, obscure an impact, or leave a foreseeable question unanswered. Reconcile their findings; a simulated objection is a reason to inspect the wording, not proof that the audience will react that way. Check dates, decisions, promises, and instructions against sources and revise.
Deliver the finished announcement as an editable document when supported, otherwise as complete ready-to-use text. Include brief separate notes on important audience questions, the evidence behind consequential wording choices, and any unresolved details needing my decision. If missing information prevents a final announcement, clearly mark the draft and its exact unfinished commitments rather than claiming it is ready. Stop after this preparation; do not send or publish the announcement.
Done when
You have a revised announcement whose facts and commitments match the available record, plus the important audience questions and any specific decisions still needed before use.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.