Get a daily quick tip on ways to improve.
A small suggestion can change the next conversation: name the decision you need before giving the background, leave an extra beat after asking a question, or reuse the way you explained something particularly well last week. Let AI find those opportunities in your actual work and send one quick, positive tip a day. You can read it in a moment and try it when the opportunity comes.
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
- Looks through accessible feedback, email, chat and meeting transcripts for small ways to make your everyday work go better, including strengths you could use more often.
- Gives you one brief, encouraging tip connected to something you are actually doing, and adjusts future tips to your reactions.
- Investigates how to deliver the tips daily in your existing tools and tests the arrangement it can actually set up.
What to have ready
- Access to the work records you are comfortable using; rough feedback or a few examples can also get this started.
- An area you want to improve, if one is already on your mind.
Where you come in
- Correct the AI’s reading of your work and choose a useful focus.
- Choose when and where the tip should arrive, then occasionally say what helped or missed the mark.
What you'll get
A practical first tip and a reusable, personalized daily tip routine, with automatic delivery tested where available and an easy manual route otherwise.
You're done when
You have received a useful first tip, chosen its daily delivery arrangement, and have a routine that can carry your feedback into future tips. Automatic delivery has been tested if it is available; otherwise you have a clearly identified manual routine and its reusable instructions.
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. ### Purpose and working material Help me get a daily quick tip on ways to improve. Make this encouraging, specific and easy to use: one small move I can try in my real work, including ways to build on something I already do well. Use my existing feedback and work records to discover opportunities. A tip should fit into the day I already have. Start with anything I supplied and inspect the tools and sources you can actually use. Try relevant access rather than assuming a listed connection works. Look through accessible sent and received emails, human chat history including WhatsApp where available, meeting transcripts, feedback documents, recent work products and calendar context. Search for concrete feedback, questions people repeatedly ask me, examples that led to clarity or progress, points where a conversation stalled, and techniques I used successfully. Use names, project terms and dates from the initial material to find related exchanges and see the outcome, not just an isolated line. Keep a compact source and coverage record. For a large history, divide it by date, project or source into manageable passes. If agents are available and the volume justifies it, give separate bounded source reviews the question, actual records, citation requirements and a request for both effective behaviors and practical opportunities. Reconcile their findings against the source material yourself. Without agents, use successive passes and save the evidence and remaining coverage between them. If access is missing, research the actual tool's documented connection or export options and attempt the available route. Ask for the smallest action I must take. A few pasted exchanges, feedback notes or transcripts are a valid starting point; say what that narrower view can support. Do not turn incomplete coverage into a verdict on my abilities. ### Find a useful starting point Show me a short, positive account of what you found: what appears to work well, two or three practical opportunities, and the evidence behind each. Separate explicit feedback, observable events and your interpretation. Account for context and conflicting examples. Other people's responses are evidence of those exchanges, not proof of their motives or of a fixed trait in me. Ask one focused question about which opportunity would be most useful now, unless I have already made that clear, and wait for my answer. Let me correct your interpretation or suggest another focus. Store the chosen focus and my corrections in a small editable preference record in a location the setup can actually retain; if persistence is unavailable, give me a compact file or text block to reuse. ### Give me the first quick tip Produce one tip immediately after the focus is clear. Include: - A short, inviting title. - One concrete action, described in a few sentences. - A phrase I could use or a tiny before-and-after example drawn from my kind of work. - A suitable moment to try it, using my upcoming work or calendar when accessible. - A brief reason this may help, with a source reference available for the work example behind it. For example, a tip might be: “Before the next update, write the one choice you need from the group. Open with that sentence, then give the background.” Match the suggestion to the actual evidence; this example is not a diagnosis or default assignment. Keep the tone warm, practical and respectful. Avoid converting a quick tip into a mandatory course, test, score or personality assessment. Ask whether this tip felt relevant and easy to try. Incorporate my answer before designing more editions. ### Arrange the daily routine Ask when I want the tip, my time zone and the delivery place, using existing preferences where available. Inspect the current scheduling, retrieval, storage and delivery tools; consult their current official documentation where necessary. Explain the simplest workable arrangement and carry out the authorized setup. Ask only for a missing decision or action that affects it. Do not promise that this chat can wake up or retrieve new records if it cannot. The recurring instructions must load my focus and preferences, inspect newly accessible feedback and relevant work since the last run, check previous tips to avoid repetition, and produce one useful next suggestion. New material should improve relevance; do not manufacture a fresh observation when nothing new is available. Preserve a brief history of tips, my reactions and the source coverage needed to continue in a later session. Make the feedback easy: I can reply “useful,” “not relevant,” “too much,” “more like this,” or an ordinary sentence. Treat a skipped reply as no feedback. Adapt the next tip's topic, tone, length and examples to what I actually say. When my work changes, check whether the focus should change too. ### Test and leave a usable result Run a sample through the chosen delivery route and check that its time zone, destination, text and retained preferences are correct. Confirm the schedule's actual enabled state and show me how to change or stop it. If automatic delivery is unavailable, deliver the first tip, the saved preferences and a ready-to-run daily prompt or file, with the specific remaining setup step clearly identified. A manual routine is the fallback result; an untested schedule is not working delivery. Finish with my first tip, the chosen focus, where the routine and preferences live, what was successfully tested, and anything still required for automation. Keep the technical explanation brief enough that I can start using the tip. 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 a daily quick tip on ways to improve.
What the AI will do
- Looks through accessible feedback, email, chat and meeting transcripts for small ways to make your everyday work go better, including strengths you could use more often.
- Gives you one brief, encouraging tip connected to something you are actually doing, and adjusts future tips to your reactions.
- Investigates how to deliver the tips daily in your existing tools and tests the arrangement it can actually set up.
What you can provide
- Access to the work records you are comfortable using; rough feedback or a few examples can also get this started.
- An area you want to improve, if one is already on your mind.
Where you'll take part
- Correct the AI’s reading of your work and choose a useful focus.
- Choose when and where the tip should arrive, then occasionally say what helped or missed the mark.
What you'll get
A practical first tip and a reusable, personalized daily tip routine, with automatic delivery tested where available and an easy manual route otherwise.
Activity context
A small suggestion can change the next conversation: name the decision you need before giving the background, leave an extra beat after asking a question, or reuse the way you explained something particularly well last week. Let AI find those opportunities in your actual work and send one quick, positive tip a day. You can read it in a moment and try it when the opportunity comes.
For the user
Use an AI that can work with your email, messages, documents or meeting transcripts, if available. You can also start with feedback or a few rough examples you already have. The AI will investigate before asking you to reconstruct your work, check its interpretation with you, and give you a first tip. You will choose the delivery time and place; a quick reaction to later tips will help it learn what is useful.
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
Purpose and working material
Help me get a daily quick tip on ways to improve. Make this encouraging, specific and easy to use: one small move I can try in my real work, including ways to build on something I already do well. Use my existing feedback and work records to discover opportunities. A tip should fit into the day I already have.
Start with anything I supplied and inspect the tools and sources you can actually use. Try relevant access rather than assuming a listed connection works. Look through accessible sent and received emails, human chat history including WhatsApp where available, meeting transcripts, feedback documents, recent work products and calendar context. Search for concrete feedback, questions people repeatedly ask me, examples that led to clarity or progress, points where a conversation stalled, and techniques I used successfully. Use names, project terms and dates from the initial material to find related exchanges and see the outcome, not just an isolated line.
Keep a compact source and coverage record. For a large history, divide it by date, project or source into manageable passes. If agents are available and the volume justifies it, give separate bounded source reviews the question, actual records, citation requirements and a request for both effective behaviors and practical opportunities. Reconcile their findings against the source material yourself. Without agents, use successive passes and save the evidence and remaining coverage between them.
If access is missing, research the actual tool's documented connection or export options and attempt the available route. Ask for the smallest action I must take. A few pasted exchanges, feedback notes or transcripts are a valid starting point; say what that narrower view can support. Do not turn incomplete coverage into a verdict on my abilities.
Find a useful starting point
Show me a short, positive account of what you found: what appears to work well, two or three practical opportunities, and the evidence behind each. Separate explicit feedback, observable events and your interpretation. Account for context and conflicting examples. Other people's responses are evidence of those exchanges, not proof of their motives or of a fixed trait in me.
Ask one focused question about which opportunity would be most useful now, unless I have already made that clear, and wait for my answer. Let me correct your interpretation or suggest another focus. Store the chosen focus and my corrections in a small editable preference record in a location the setup can actually retain; if persistence is unavailable, give me a compact file or text block to reuse.
Give me the first quick tip
Produce one tip immediately after the focus is clear. Include:
- A short, inviting title.
- One concrete action, described in a few sentences.
- A phrase I could use or a tiny before-and-after example drawn from my kind of work.
- A suitable moment to try it, using my upcoming work or calendar when accessible.
- A brief reason this may help, with a source reference available for the work example behind it.
For example, a tip might be: “Before the next update, write the one choice you need from the group. Open with that sentence, then give the background.” Match the suggestion to the actual evidence; this example is not a diagnosis or default assignment.
Keep the tone warm, practical and respectful. Avoid converting a quick tip into a mandatory course, test, score or personality assessment. Ask whether this tip felt relevant and easy to try. Incorporate my answer before designing more editions.
Arrange the daily routine
Ask when I want the tip, my time zone and the delivery place, using existing preferences where available. Inspect the current scheduling, retrieval, storage and delivery tools; consult their current official documentation where necessary. Explain the simplest workable arrangement and carry out the authorized setup. Ask only for a missing decision or action that affects it. Do not promise that this chat can wake up or retrieve new records if it cannot.
The recurring instructions must load my focus and preferences, inspect newly accessible feedback and relevant work since the last run, check previous tips to avoid repetition, and produce one useful next suggestion. New material should improve relevance; do not manufacture a fresh observation when nothing new is available. Preserve a brief history of tips, my reactions and the source coverage needed to continue in a later session.
Make the feedback easy: I can reply “useful,” “not relevant,” “too much,” “more like this,” or an ordinary sentence. Treat a skipped reply as no feedback. Adapt the next tip's topic, tone, length and examples to what I actually say. When my work changes, check whether the focus should change too.
Test and leave a usable result
Run a sample through the chosen delivery route and check that its time zone, destination, text and retained preferences are correct. Confirm the schedule's actual enabled state and show me how to change or stop it. If automatic delivery is unavailable, deliver the first tip, the saved preferences and a ready-to-run daily prompt or file, with the specific remaining setup step clearly identified. A manual routine is the fallback result; an untested schedule is not working delivery.
Finish with my first tip, the chosen focus, where the routine and preferences live, what was successfully tested, and anything still required for automation. Keep the technical explanation brief enough that I can start using the tip.
Done when
You have received a useful first tip, chosen its daily delivery arrangement, and have a routine that can carry your feedback into future tips. Automatic delivery has been tested if it is available; otherwise you have a clearly identified manual routine and its reusable instructions.
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.