Find the ask in a confusing email.
Some emails contain three paragraphs of context and half a sentence of request. Have AI work out what is actually being asked of you.
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
- Find the requested action, owner, timing, and dependencies using the email and relevant surrounding records.
What to have ready
- The email or thread; related material can be found through available connections or shared in any usable form.
Where you come in
- Clarify important uncertainties and decide how to handle any request the sender has left ambiguous.
What you'll get
You have a clear account of what is being asked, what remains uncertain, and a concise clarification or acknowledgment ready to use if needed.
You're done when
You have a clear account of what is being asked, what remains uncertain, and a concise clarification or acknowledgment ready to use if needed.
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. Help me understand what this confusing email is asking me to do. ### 1. Read the request in context. Read the complete email, including relevant quoted messages, attachments, and linked documents you can access. Identify the sender, recipient, date, and subject. Distinguish the sender’s new message from forwarded or quoted older requests. Check available email, messaging and chat connectors, meeting transcripts, documents, and project files for the specific issue. Search references, people, dates, and projects from the email. Look for earlier agreements, definitions, deadlines, and later messages that clarify or withdraw a request. Avoid assuming that the most recent document is authoritative merely because its file timestamp is newer. Say upfront if the email admits materially different readings. Explain what the sources establish and what they leave ambiguous. Ask me a focused question when my context could resolve the ambiguity; wait before using an answer you do not have. If the sender must clarify it, prepare that question for them rather than asking me to guess. ### 2. Extract the asks. Separate background information, opinion, optional suggestions, and actual requests. For each requested action, identify: - What needs to be done or decided, and what output would satisfy it. - Who appears responsible, distinguishing me from other recipients. - The deadline, including whether it is explicit, inferred, or absent. - Dependencies or information needed before action is possible. Use dates and source references where they help. Do not turn “soon” into an invented deadline or an open discussion into an instruction. Acknowledge when the email contains no actionable request. If two interpretations remain plausible, state them concretely and explain what answer would distinguish them. ### 3. Give me a usable reading and response. Lead with a plain-language account of the ask, followed by the important uncertainty. Keep it proportionate to the email: a simple request needs a short explanation, while several linked asks may need a compact list or table. Draft a brief acknowledgment or clarification if useful. It should confirm only what is supported and ask the smallest question that resolves the remaining issue. Avoid committing me to work, dates, or a position I have not accepted. Check the explanation and draft against the original email and relevant context, incorporate my corrections, and finish with the clarified request and any ready-to-use response. Do not perform the requested work or send the reply within this activity unless I separately ask. 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
Find the ask in a confusing email.
What the AI will do
- Find the requested action, owner, timing, and dependencies using the email and relevant surrounding records.
What you can provide
- The email or thread; related material can be found through available connections or shared in any usable form.
Where you'll take part
- Clarify important uncertainties and decide how to handle any request the sender has left ambiguous.
What you'll get
You have a clear account of what is being asked, what remains uncertain, and a concise clarification or acknowledgment ready to use if needed.
Activity context
Some emails contain three paragraphs of context and half a sentence of request. Have AI work out what is actually being asked of you.
For the user
Share the email or thread. The AI can look through relevant connected messages and documents to clarify what it refers to. You’ll answer any question the record cannot settle and can choose a short clarification to send back.
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
Help me understand what this confusing email is asking me to do.
1. Read the request in context.
Read the complete email, including relevant quoted messages, attachments, and linked documents you can access. Identify the sender, recipient, date, and subject. Distinguish the sender’s new message from forwarded or quoted older requests.
Check available email, messaging and chat connectors, meeting transcripts, documents, and project files for the specific issue. Search references, people, dates, and projects from the email. Look for earlier agreements, definitions, deadlines, and later messages that clarify or withdraw a request. Avoid assuming that the most recent document is authoritative merely because its file timestamp is newer.
Say upfront if the email admits materially different readings. Explain what the sources establish and what they leave ambiguous. Ask me a focused question when my context could resolve the ambiguity; wait before using an answer you do not have. If the sender must clarify it, prepare that question for them rather than asking me to guess.
2. Extract the asks.
Separate background information, opinion, optional suggestions, and actual requests. For each requested action, identify:
- What needs to be done or decided, and what output would satisfy it.
- Who appears responsible, distinguishing me from other recipients.
- The deadline, including whether it is explicit, inferred, or absent.
- Dependencies or information needed before action is possible.
Use dates and source references where they help. Do not turn “soon” into an invented deadline or an open discussion into an instruction. Acknowledge when the email contains no actionable request. If two interpretations remain plausible, state them concretely and explain what answer would distinguish them.
3. Give me a usable reading and response.
Lead with a plain-language account of the ask, followed by the important uncertainty. Keep it proportionate to the email: a simple request needs a short explanation, while several linked asks may need a compact list or table.
Draft a brief acknowledgment or clarification if useful. It should confirm only what is supported and ask the smallest question that resolves the remaining issue. Avoid committing me to work, dates, or a position I have not accepted. Check the explanation and draft against the original email and relevant context, incorporate my corrections, and finish with the clarified request and any ready-to-use response. Do not perform the requested work or send the reply within this activity unless I separately ask.
Done when
You have a clear account of what is being asked, what remains uncertain, and a concise clarification or acknowledgment ready to use if needed.
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.