Get the TL;DR on a confusing deck.
Find out what the deck is trying to tell you, what it actually establishes, and what it wants you to do.
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
- Read the actual slides and investigate the sending context, related discussions, and underlying evidence.
- Explain the argument with slide references, separating the deck’s claims from contextual clarification and unresolved gaps.
What to have ready
- The confusing deck or its link; the sending message or meeting name is useful if available.
Where you come in
- Clarify what you need from the deck if the surrounding context does not establish it; ask for a closer look at any consequential gap.
What you'll get
You have a concise, traceable account of the deck’s point, evidence, and requested decision, with the important unanswered questions made clear.
You're done when
You have a concise, traceable account of the deck’s point, evidence, and requested decision, with the important unanswered questions made clear.
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 get the TL;DR on a confusing deck. Explain its argument in plain language, show what supports it, and tell me what decision or response it seeks. Keep the final account concise while doing enough investigation to avoid a confidently wrong simplification. ### 1. Obtain the actual deck and understand my use Open the supplied file or link and check that you can inspect the slides, charts, tables, diagrams, and available speaker notes. Identify the title, date or version, author, and page count. If extraction loses visual meaning, render or inspect the slides directly. Use stable slide numbers; distinguish printed slide labels from file page numbers when they differ. Find the sending email or chat, calendar invitation and attendee list, agenda, related meeting records, project documents, and relevant company data. Search by deck title, sender, project, date, and distinctive phrases. Establish why the deck was shared, what meeting or decision it serves, and my role in it. Use attendee roles and their actual comments or questions to understand the audience's concerns; do not invent what they think. If my purpose remains unclear, ask a focused question, such as whether I need to understand the proposal or prepare to decide on it. Wait on a purpose-dependent recommendation while continuing the factual read. Do not require a briefing packet before trying relevant access. ### 2. Establish what the deck actually contains Make an internal map of the full deck: each slide's main claim, its evidence or example, and its role in the argument. Inspect appendices that qualify central claims. Note unexplained terminology, jumps in logic, conflicting numbers, and charts whose labels or visual encoding change the apparent message. Separate three things throughout: - What the deck explicitly says or shows, with slide references. - What related records clarify, with their own source references. - Your interpretation, or a question the available material does not answer. Trace central figures to available underlying tables, definitions, or project data. Check units, denominators, time periods, comparison groups, and whether the visual actually supports the accompanying claim. Do not attempt an unlimited audit of every number; investigate the figures on which the deck's conclusion depends and make the remaining verification limits visible. For a large deck or source set, divide reading among bounded agents by coherent sections, not arbitrary chunks that sever an argument. Give each the deck map, exact slide range or sources, the purpose, and a return format covering claims, evidence, qualifications, questions, and references. Use fresh contexts, and let independent reads finish before synthesis. Maintain coverage of all slides, including appendices. With limited capacity, use successive waves or fresh-session handoffs carrying the source index and unresolved cross-section links. A long input is not proof that every slide was inspected. ### 3. Reconstruct and test the argument Write the argument privately as a short chain: situation, problem or opportunity, proposed explanation or action, supporting evidence, and requested decision. Identify which links are explicit and which you supplied to make sense of it. Compare the beginning, conclusion, and detailed slides; a conclusion can claim more than the body establishes. Use related emails, chats, meeting transcripts, calendar-linked discussions, project records, and company data to clarify ambiguous references and detect later amendments. Preserve the distinction between the deck's position when written and a subsequently changed decision. If records disagree, describe the disagreement instead of silently repairing the deck. Ask me only about gaps my answer could materially resolve. If two interpretations remain credible, state both and what evidence would distinguish them. Do not force a coherent thesis when the deck contains competing proposals or no clear ask. ### 4. Deliver the useful short version Lead with a plain-language explanation of the central point and what, if anything, I am being asked to decide. Then provide a compact account containing: - The few claims needed to understand the argument, with slide references. - The strongest supporting evidence and its consequential qualification. - The requested action, owner, or deadline, if actually established. - The important missing link or unanswered question that could change the decision. Translate jargon accurately and retain distinctions that matter. Put detailed source notes after the short version so they do not overwhelm it. If the evidence cannot establish a single point or decision, say so and explain the competing readings briefly. Check every summary claim against the slides or its separately identified contextual source. If useful, have a fresh reviewer reconstruct the argument from the deck and test your summary for overstatement and omissions; repair discrepancies. A same-context reread is a fallback, not an independent verdict. If the deck or essential slides cannot be accessed, investigate export or upload options and help me obtain a readable version. Do not claim to summarize unseen slides. A partial deck permits a labeled partial account with the missing coverage stated. Finish with the actual TL;DR and consequential questions, not a plan to summarize later. 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
Get the TL;DR on a confusing deck.
What the AI will do
- Read the actual slides and investigate the sending context, related discussions, and underlying evidence.
- Explain the argument with slide references, separating the deck’s claims from contextual clarification and unresolved gaps.
What you can provide
- The confusing deck or its link; the sending message or meeting name is useful if available.
Where you'll take part
- Clarify what you need from the deck if the surrounding context does not establish it; ask for a closer look at any consequential gap.
What you'll get
You have a concise, traceable account of the deck’s point, evidence, and requested decision, with the important unanswered questions made clear.
Activity context
Find out what the deck is trying to tell you, what it actually establishes, and what it wants you to do.
For the user
Share the deck as it is. The AI will read its text and visuals, find the relevant context where access permits, and give you the short account you need before a meeting or decision. It may ask one clarifying question about your purpose.
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 get the TL;DR on a confusing deck. Explain its argument in plain language, show what supports it, and tell me what decision or response it seeks. Keep the final account concise while doing enough investigation to avoid a confidently wrong simplification.
1. Obtain the actual deck and understand my use
Open the supplied file or link and check that you can inspect the slides, charts, tables, diagrams, and available speaker notes. Identify the title, date or version, author, and page count. If extraction loses visual meaning, render or inspect the slides directly. Use stable slide numbers; distinguish printed slide labels from file page numbers when they differ.
Find the sending email or chat, calendar invitation and attendee list, agenda, related meeting records, project documents, and relevant company data. Search by deck title, sender, project, date, and distinctive phrases. Establish why the deck was shared, what meeting or decision it serves, and my role in it. Use attendee roles and their actual comments or questions to understand the audience's concerns; do not invent what they think.
If my purpose remains unclear, ask a focused question, such as whether I need to understand the proposal or prepare to decide on it. Wait on a purpose-dependent recommendation while continuing the factual read. Do not require a briefing packet before trying relevant access.
2. Establish what the deck actually contains
Make an internal map of the full deck: each slide's main claim, its evidence or example, and its role in the argument. Inspect appendices that qualify central claims. Note unexplained terminology, jumps in logic, conflicting numbers, and charts whose labels or visual encoding change the apparent message.
Separate three things throughout:
- What the deck explicitly says or shows, with slide references.
- What related records clarify, with their own source references.
- Your interpretation, or a question the available material does not answer.
Trace central figures to available underlying tables, definitions, or project data. Check units, denominators, time periods, comparison groups, and whether the visual actually supports the accompanying claim. Do not attempt an unlimited audit of every number; investigate the figures on which the deck's conclusion depends and make the remaining verification limits visible.
For a large deck or source set, divide reading among bounded agents by coherent sections, not arbitrary chunks that sever an argument. Give each the deck map, exact slide range or sources, the purpose, and a return format covering claims, evidence, qualifications, questions, and references. Use fresh contexts, and let independent reads finish before synthesis. Maintain coverage of all slides, including appendices. With limited capacity, use successive waves or fresh-session handoffs carrying the source index and unresolved cross-section links. A long input is not proof that every slide was inspected.
3. Reconstruct and test the argument
Write the argument privately as a short chain: situation, problem or opportunity, proposed explanation or action, supporting evidence, and requested decision. Identify which links are explicit and which you supplied to make sense of it. Compare the beginning, conclusion, and detailed slides; a conclusion can claim more than the body establishes.
Use related emails, chats, meeting transcripts, calendar-linked discussions, project records, and company data to clarify ambiguous references and detect later amendments. Preserve the distinction between the deck's position when written and a subsequently changed decision. If records disagree, describe the disagreement instead of silently repairing the deck.
Ask me only about gaps my answer could materially resolve. If two interpretations remain credible, state both and what evidence would distinguish them. Do not force a coherent thesis when the deck contains competing proposals or no clear ask.
4. Deliver the useful short version
Lead with a plain-language explanation of the central point and what, if anything, I am being asked to decide. Then provide a compact account containing:
- The few claims needed to understand the argument, with slide references.
- The strongest supporting evidence and its consequential qualification.
- The requested action, owner, or deadline, if actually established.
- The important missing link or unanswered question that could change the decision.
Translate jargon accurately and retain distinctions that matter. Put detailed source notes after the short version so they do not overwhelm it. If the evidence cannot establish a single point or decision, say so and explain the competing readings briefly.
Check every summary claim against the slides or its separately identified contextual source. If useful, have a fresh reviewer reconstruct the argument from the deck and test your summary for overstatement and omissions; repair discrepancies. A same-context reread is a fallback, not an independent verdict.
If the deck or essential slides cannot be accessed, investigate export or upload options and help me obtain a readable version. Do not claim to summarize unseen slides. A partial deck permits a labeled partial account with the missing coverage stated. Finish with the actual TL;DR and consequential questions, not a plan to summarize later.
Done when
You have a concise, traceable account of the deck’s point, evidence, and requested decision, with the important unanswered questions made clear.
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.