Photograph a receipt and say, “Log this.”
Photograph a receipt and ask AI to log it. It can read the details, look for the expense system you use, and use your projects and travel schedule to work out where the expense belongs. You check anything it cannot confidently establish.
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 receipt and investigate your expense system, project and travel context.
- Prepare and save the entry where access permits, then verify it.
What to have ready
- A receipt photo, image or PDF.
Where you come in
- Clarify uncertain details and review the expense entry.
What you'll get
A checked expense entry, or a prepared record with an explicit remaining logging step.
You're done when
The receipt is saved in the right expense system with its details checked—or you have a ready-to-enter record and know exactly what remains to log it.
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. ### Read the receipt and find where it belongs Log this receipt in the expense system I use. Read the merchant, date, amount, currency, tax and line items where relevant. Flag an unreadable value rather than guessing it; ask for another photo only if needed. Try accessible expense-policy documents, previous expense records, software references in company emails or chats, and relevant app connections to identify my expense system and the fields it requires. Search my calendar, travel bookings and relevant project correspondence around the receipt date to establish the trip, project, business purpose and likely cost code. Keep this focused on the expense. Check for an existing matching transaction or receipt so we do not log it twice. Use confirmed context to fill the record. Ask one short question about anything consequential still unclear, such as which of two projects the expense belongs to. Distinguish the printed amount and date from inferred purpose or category. Do not invent attendees, convert currencies using a guessed rate, or assume every item is reimbursable; follow the actual system and policy where available. ### Log it and check the result Inspect whether you can create or update the expense through the available connection. If access is missing, investigate the supported import or entry route for my actual system, then help me take the smallest necessary access step. Prepare the exact fields while doing that. Show a compact record for review, including the receipt attachment, amount, date, currency, purpose and category or project. Once unresolved choices are settled, save it as an expense entry or draft within my request. Submitting a reimbursement claim, sending it for approval or initiating payment is a separate action; do that only if I ask. Read back the saved record or system confirmation and report where it was logged. If you cannot write to the system, give me the ready-to-enter record or supported import file and the exact remaining step. Say clearly that it has not been logged yet. A formatted table alone is not evidence of a saved expense. 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
Photograph a receipt and say, “Log this.”
Photograph a receipt and ask AI to log it. It can read the details, look for the expense system you use, and use your projects and travel schedule to work out where the expense belongs. You check anything it cannot confidently establish.
For the user
Take a readable photo of the receipt on your phone and give it to the AI with this prompt. An existing photo or receipt PDF works too.
Done when
The receipt is saved in the right expense system with its details checked—or you have a ready-to-enter record and know exactly what remains to log it.
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
Read the receipt and find where it belongs
Log this receipt in the expense system I use. Read the merchant, date, amount, currency, tax and line items where relevant. Flag an unreadable value rather than guessing it; ask for another photo only if needed.
Try accessible expense-policy documents, previous expense records, software references in company emails or chats, and relevant app connections to identify my expense system and the fields it requires. Search my calendar, travel bookings and relevant project correspondence around the receipt date to establish the trip, project, business purpose and likely cost code. Keep this focused on the expense. Check for an existing matching transaction or receipt so we do not log it twice.
Use confirmed context to fill the record. Ask one short question about anything consequential still unclear, such as which of two projects the expense belongs to. Distinguish the printed amount and date from inferred purpose or category. Do not invent attendees, convert currencies using a guessed rate, or assume every item is reimbursable; follow the actual system and policy where available.
Log it and check the result
Inspect whether you can create or update the expense through the available connection. If access is missing, investigate the supported import or entry route for my actual system, then help me take the smallest necessary access step. Prepare the exact fields while doing that.
Show a compact record for review, including the receipt attachment, amount, date, currency, purpose and category or project. Once unresolved choices are settled, save it as an expense entry or draft within my request. Submitting a reimbursement claim, sending it for approval or initiating payment is a separate action; do that only if I ask.
Read back the saved record or system confirmation and report where it was logged. If you cannot write to the system, give me the ready-to-enter record or supported import file and the exact remaining step. Say clearly that it has not been logged yet. A formatted table alone is not evidence of a saved expense.
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.