Turn a screen recording into step-by-step instructions.
Do the task once on screen. Have AI turn the recording into instructions someone else can follow.
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
- Reconstruct the demonstrated workflow and create clear instructions with decision points and screenshots where supported.
What to have ready
- A screen recording, or screenshots with a narrated sequence; the intended reader or related process documents if you have them.
Where you come in
- Clarify actions the recording does not explain, choose the useful level of detail, and help check steps the AI cannot test.
What you'll get
You have a usable how-to guide grounded in the supplied material, with necessary context, images where supported, and an accurate account of which steps were verified.
You're done when
You have a usable how-to guide grounded in the supplied material, with necessary context, images where supported, and an accurate account of which steps were verified.
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. Turn this screen recording into clear step-by-step instructions for someone else to follow. ### 1. Understand the workflow and its reader. Inspect the recording using available video, audio, transcript, or frame-extraction tools. Establish which parts you can actually see or hear. If direct video access is unavailable, help me share a supported export, screenshots, or a narrated sequence; do not describe unseen actions as observed. Identify the task’s starting state, intended result, applications involved, and likely audience. Search relevant available emails, messages and chats, meeting transcripts, process documents, and project files for prerequisites, terminology, permissions, and reasons for the workflow. Separate current instructions from older versions. Ask a focused question if the reader’s knowledge or intended use changes how to explain the task. Offer a concise checklist for experienced users or a fuller illustrated guide for newcomers when those alternatives would help. Wait for a consequential choice; otherwise use the evident audience and purpose. ### 2. Reconstruct what actually happens. Review the complete accessible recording or fallback sequence before settling the steps. Identify each purposeful action, the visible control or field involved, the input, and the expected response. Note pauses, errors, reversals, shortcuts, and branches. Distinguish necessary actions from accidental clicks or repetition. Record source timestamps where available; otherwise use identifiable screenshot, passage, or step references. State any gaps in coverage. Look for actions that may be invisible, such as a keyboard shortcut, preexisting login, background calculation, or copied value. Use supporting material to clarify them and ask when the answer affects whether the guide can be followed. Do not fill a missing step with a confident invention. If the demonstrated method is outdated or appears mistaken, explain the issue and offer a corrected route separately before replacing the demonstrated one. ### 3. Write the guide. Start with the result, prerequisites, and starting state. Write numbered actions in a logical sequence, using recognizable interface labels and explaining what the reader should see after important steps. Put branch conditions next to the action they change. Use descriptive example values instead of unexplained data from the recording. Capture or use supplied screenshots at useful moments where tools allow, crop for clarity, and label relevant controls. Keep sensitive or incidental values out of reusable examples. Distinguish observed actions from explanations or additional steps supported by other sources. Include likely recovery points only where the recording or reliable documentation supports them. ### 4. Check and deliver. - Walk through the guide against the complete accessible source sequence from start to finish. - Check missing prerequisites, unexplained transitions, incorrect labels, and steps that would leave the reader in the wrong state. - Try safe, permitted steps with available tools when practical. - Ask me to verify a specific step only if necessary access is unavailable; explain exactly what result to look for. Deliver a complete editable guide with images where supported and source timestamps or other references where useful. If embedded images are unsupported, provide a text guide with clearly linked image files or source moments. Incorporate corrections and state what was checked against the supplied material versus actually tried. Do not equate a written walkthrough with a successful execution of the underlying workflow. 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
Turn a screen recording into step-by-step instructions.
What the AI will do
- Reconstruct the demonstrated workflow and create clear instructions with decision points and screenshots where supported.
What you can provide
- A screen recording, or screenshots with a narrated sequence; the intended reader or related process documents if you have them.
Where you'll take part
- Clarify actions the recording does not explain, choose the useful level of detail, and help check steps the AI cannot test.
What you'll get
You have a usable how-to guide grounded in the supplied material, with necessary context, images where supported, and an accurate account of which steps were verified.
Activity context
Do the task once on screen. Have AI turn the recording into instructions someone else can follow.
For the user
Share the screen recording, or a supported combination of screenshots and narration. The AI can consult related process notes and project files. You’ll clarify hidden steps or choices and help verify any part that only a person with your access can try.
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
Turn this screen recording into clear step-by-step instructions for someone else to follow.
1. Understand the workflow and its reader.
Inspect the recording using available video, audio, transcript, or frame-extraction tools. Establish which parts you can actually see or hear. If direct video access is unavailable, help me share a supported export, screenshots, or a narrated sequence; do not describe unseen actions as observed.
Identify the task’s starting state, intended result, applications involved, and likely audience. Search relevant available emails, messages and chats, meeting transcripts, process documents, and project files for prerequisites, terminology, permissions, and reasons for the workflow. Separate current instructions from older versions.
Ask a focused question if the reader’s knowledge or intended use changes how to explain the task. Offer a concise checklist for experienced users or a fuller illustrated guide for newcomers when those alternatives would help. Wait for a consequential choice; otherwise use the evident audience and purpose.
2. Reconstruct what actually happens.
Review the complete accessible recording or fallback sequence before settling the steps. Identify each purposeful action, the visible control or field involved, the input, and the expected response. Note pauses, errors, reversals, shortcuts, and branches. Distinguish necessary actions from accidental clicks or repetition.
Record source timestamps where available; otherwise use identifiable screenshot, passage, or step references. State any gaps in coverage. Look for actions that may be invisible, such as a keyboard shortcut, preexisting login, background calculation, or copied value. Use supporting material to clarify them and ask when the answer affects whether the guide can be followed. Do not fill a missing step with a confident invention. If the demonstrated method is outdated or appears mistaken, explain the issue and offer a corrected route separately before replacing the demonstrated one.
3. Write the guide.
Start with the result, prerequisites, and starting state. Write numbered actions in a logical sequence, using recognizable interface labels and explaining what the reader should see after important steps. Put branch conditions next to the action they change. Use descriptive example values instead of unexplained data from the recording.
Capture or use supplied screenshots at useful moments where tools allow, crop for clarity, and label relevant controls. Keep sensitive or incidental values out of reusable examples. Distinguish observed actions from explanations or additional steps supported by other sources. Include likely recovery points only where the recording or reliable documentation supports them.
4. Check and deliver.
- Walk through the guide against the complete accessible source sequence from start to finish.
- Check missing prerequisites, unexplained transitions, incorrect labels, and steps that would leave the reader in the wrong state.
- Try safe, permitted steps with available tools when practical.
- Ask me to verify a specific step only if necessary access is unavailable; explain exactly what result to look for.
Deliver a complete editable guide with images where supported and source timestamps or other references where useful. If embedded images are unsupported, provide a text guide with clearly linked image files or source moments. Incorporate corrections and state what was checked against the supplied material versus actually tried. Do not equate a written walkthrough with a successful execution of the underlying workflow.
Done when
You have a usable how-to guide grounded in the supplied material, with necessary context, images where supported, and an accurate account of which steps were verified.
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.