Evaluate all projects against the firm’s values.
Company values become revealing when a project makes them expensive to honor. Examine the actual portfolio against what the firm says it values, first getting clear about what those words require in practice. Find the projects that demonstrate the values, the ones that create tension and the decisions that need an honest tradeoff.
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 firm’s stated values and clarify their practical meaning with you before evaluating projects.
- Map the current portfolio and examine project choices, incentives, resource decisions and stakeholder evidence.
- Produce supported findings on alignment and tension, with proposed changes and unresolved value choices.
What to have ready
- The company and portfolio to examine, with access to values statements, project records and related communications where available.
- Your understanding of the values, especially where official language is vague or different versions conflict.
Where you come in
- Work through a few concrete edge cases and agree the interpretations used for the review.
- Confirm portfolio coverage, resolve consequential value conflicts and review proposed changes.
What you'll get
You receive a project-level review against agreed interpretations of the firm’s values, with evidence and proposed actions; the report states exactly which projects it covers.
You're done when
You have an evidence-based review of the agreed portfolio against explicit working interpretations of the firm's values, including supported alignment, concrete tensions, proposed changes and visible gaps in coverage.
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. ### 1. Find the values and their authority Help me evaluate our current projects against the firm's values. Establish the company and portfolio scope from the supplied context, asking one focused question where necessary. Inspect and try relevant access to company documents, email, chats and other messages, calendar-linked leadership meetings and transcripts, and project systems. Search the corporate website, employee handbooks, onboarding material, published values, strategy presentations, leadership communications and relevant policies. Use official terms and examples to find how people explain and apply the values in decisions. Record the exact wording, source, authority, date and scope of each value. Distinguish an official current statement from an old version, a leader's interpretation or a local team's practice. Trace a superseding decision if versions differ; a newer upload alone does not establish a change. Show unresolved conflicts rather than selecting the wording most convenient for evaluation. If access is missing, inspect available connection or export options and explain which sources would help. Ask for specific missing materials and offer to draft a focused access request if useful. A public values page can start the work; project claims require project evidence. If the company has no explicit statement we can find, ask me to articulate the values I want to examine and label them as my account throughout. ### 2. Make the values concrete with me Show the discovered values and any documented examples of their use. Ask how I understand consequential ambiguities. A slogan such as customer first or integrity may not yet tell us how to judge a project. Explore a few real or clearly hypothetical edge cases one at a time. What would the value require when honoring it costs revenue or slows delivery? What happens when two stated values conflict? If speed and transparency pull in different directions, which decision belongs to whom? Ground examples in the company's work, and distinguish evidence about the firm's position from the interpretation we are proposing. For each value, draft a practical interpretation: the relevant choices it affects, observable behaviors that would support it, behaviors that would create tension, and questions the language leaves open. Keep official wording, my interpretation and your proposed evaluation criteria in separate fields. Avoid arbitrary numerical scoring when the concepts do not support it. Ask me to correct and agree the working interpretations before applying them to projects. This agreement defines our review lens; it does not amend corporate policy or authorize you to resolve every future tradeoff. If an ambiguity cannot be settled, agree to present affected findings conditionally rather than silently choosing a definition. ### 3. Establish the actual portfolio Search project registers, operating plans, budgets, investment proposals, staffing allocations, progress reports and relevant leadership or team messages to identify current projects. Include work in discovery, delivery or material ongoing operation where it falls within the agreed definition. Reconcile aliases, parent programmes and subprojects to avoid double-counting. For each project, establish purpose, current stage, responsible role, main stakeholders, significant commitments, resources and available sources. Establish stakeholder identities and expressed concerns from roles, correspondence, meeting attendance and actual exchanges; do not invent how people feel about the project. Present the portfolio and coverage gaps for my confirmation. 'All projects' must refer to this explicitly bounded inventory and review date. Mark inaccessible projects as unassessed and ask for the most decision-relevant missing records. If only part of the portfolio can be reviewed, carry that limitation into the title of the result and conclusions. ### 4. Examine decisions and behavior project by project For each project, inspect the plan and actual choices: incentives, resource allocation, approval conditions, delivery tradeoffs, stakeholder exchanges, product or service behavior and observed outcomes. Look for where the work enacts a value, where it creates tension and where evidence is insufficient. A project description that repeats the values is a claim to investigate, not proof of alignment. Connect each finding to a specific agreed interpretation and a sourced choice or behavior. Explain who is affected and how, separating documented experience from your inference. Note stages and dates: a proposal, a funded commitment and an implemented action are different evidence. Preserve examples of strong alignment as well as problems. Where the portfolio is large, divide bounded project groups among agents with the accepted values, interpretations, exact source lists and common finding format. Require each to report assessed projects, source coverage, findings, counterevidence and open questions. Use successive waves if needed; without agents, use separate manageable passes. The lead owns a coverage record and checks that the entire agreed portfolio has a result or an explicit unassessed status. Reconcile inconsistent interpretations across reviewers before comparing projects. Trace portfolio-level tensions that individual reviews can miss—for example, several projects whose combined resource demands crowd out a stated commitment. Support that conclusion with actual allocations and dependencies rather than treating every project as equally costly. ### 5. Work through tensions and propose changes Show the most consequential supported findings first. For each tension, describe the project choice, the values involved, evidence, possible consequences and practical alternatives. Where values conflict, explain the tradeoff and ask for my judgment; do not invent a universal hierarchy or decide it silently. Use existing guidance where it actually resolves the case. Propose changes at the level the evidence supports: alter a requirement, change an incentive, add a missing stakeholder input, revise resource allocation, change a project approach or reconsider whether to continue it. Explain which value each change would serve, what it would cost or displace, and what must be clarified before choosing it. Keep recommendations separate from my decisions and leave ownership unassigned unless established. Have an independent reviewer inspect the report, accepted interpretations and necessary evidence for inconsistent standards, unsupported motives and missed counterevidence where possible. Otherwise use a separate review pass and disclose shared context. Repair material findings. ### 6. Deliver the portfolio review Provide the official values alongside the agreed working interpretations; a dated inventory with assessed and unassessed projects; project-level findings with sources; examples of demonstrated alignment; consequential tensions; and concrete proposed changes. Keep unknowns distinct from misalignment. Summarize the few decisions that need my attention and the evidence that would resolve remaining uncertainty. Review the result with me and incorporate corrections. If I choose actions, record those choices accurately. Deliver the completed assessment and proposals without modifying project systems, policies or budgets or contacting colleagues unless separately requested. 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
Evaluate all projects against the firm’s values.
What the AI will do
- Find the firm’s stated values and clarify their practical meaning with you before evaluating projects.
- Map the current portfolio and examine project choices, incentives, resource decisions and stakeholder evidence.
- Produce supported findings on alignment and tension, with proposed changes and unresolved value choices.
What you can provide
- The company and portfolio to examine, with access to values statements, project records and related communications where available.
- Your understanding of the values, especially where official language is vague or different versions conflict.
Where you'll take part
- Work through a few concrete edge cases and agree the interpretations used for the review.
- Confirm portfolio coverage, resolve consequential value conflicts and review proposed changes.
What you'll get
You receive a project-level review against agreed interpretations of the firm’s values, with evidence and proposed actions; the report states exactly which projects it covers.
Activity context
Company values become revealing when a project makes them expensive to honor. Examine the actual portfolio against what the firm says it values, first getting clear about what those words require in practice. Find the projects that demonstrate the values, the ones that create tension and the decisions that need an honest tradeoff.
For the user
Name the company and portfolio. The AI will find the stated values and project records, then discuss what the values mean in a few real situations. You will agree the working interpretations before the evaluation and make the choices where values pull in different directions.
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
1. Find the values and their authority
Help me evaluate our current projects against the firm's values. Establish the company and portfolio scope from the supplied context, asking one focused question where necessary.
Inspect and try relevant access to company documents, email, chats and other messages, calendar-linked leadership meetings and transcripts, and project systems. Search the corporate website, employee handbooks, onboarding material, published values, strategy presentations, leadership communications and relevant policies. Use official terms and examples to find how people explain and apply the values in decisions.
Record the exact wording, source, authority, date and scope of each value. Distinguish an official current statement from an old version, a leader's interpretation or a local team's practice. Trace a superseding decision if versions differ; a newer upload alone does not establish a change. Show unresolved conflicts rather than selecting the wording most convenient for evaluation.
If access is missing, inspect available connection or export options and explain which sources would help. Ask for specific missing materials and offer to draft a focused access request if useful. A public values page can start the work; project claims require project evidence. If the company has no explicit statement we can find, ask me to articulate the values I want to examine and label them as my account throughout.
2. Make the values concrete with me
Show the discovered values and any documented examples of their use. Ask how I understand consequential ambiguities. A slogan such as customer first or integrity may not yet tell us how to judge a project.
Explore a few real or clearly hypothetical edge cases one at a time. What would the value require when honoring it costs revenue or slows delivery? What happens when two stated values conflict? If speed and transparency pull in different directions, which decision belongs to whom? Ground examples in the company's work, and distinguish evidence about the firm's position from the interpretation we are proposing.
For each value, draft a practical interpretation: the relevant choices it affects, observable behaviors that would support it, behaviors that would create tension, and questions the language leaves open. Keep official wording, my interpretation and your proposed evaluation criteria in separate fields. Avoid arbitrary numerical scoring when the concepts do not support it.
Ask me to correct and agree the working interpretations before applying them to projects. This agreement defines our review lens; it does not amend corporate policy or authorize you to resolve every future tradeoff. If an ambiguity cannot be settled, agree to present affected findings conditionally rather than silently choosing a definition.
3. Establish the actual portfolio
Search project registers, operating plans, budgets, investment proposals, staffing allocations, progress reports and relevant leadership or team messages to identify current projects. Include work in discovery, delivery or material ongoing operation where it falls within the agreed definition. Reconcile aliases, parent programmes and subprojects to avoid double-counting.
For each project, establish purpose, current stage, responsible role, main stakeholders, significant commitments, resources and available sources. Establish stakeholder identities and expressed concerns from roles, correspondence, meeting attendance and actual exchanges; do not invent how people feel about the project.
Present the portfolio and coverage gaps for my confirmation. 'All projects' must refer to this explicitly bounded inventory and review date. Mark inaccessible projects as unassessed and ask for the most decision-relevant missing records. If only part of the portfolio can be reviewed, carry that limitation into the title of the result and conclusions.
4. Examine decisions and behavior project by project
For each project, inspect the plan and actual choices: incentives, resource allocation, approval conditions, delivery tradeoffs, stakeholder exchanges, product or service behavior and observed outcomes. Look for where the work enacts a value, where it creates tension and where evidence is insufficient. A project description that repeats the values is a claim to investigate, not proof of alignment.
Connect each finding to a specific agreed interpretation and a sourced choice or behavior. Explain who is affected and how, separating documented experience from your inference. Note stages and dates: a proposal, a funded commitment and an implemented action are different evidence. Preserve examples of strong alignment as well as problems.
Where the portfolio is large, divide bounded project groups among agents with the accepted values, interpretations, exact source lists and common finding format. Require each to report assessed projects, source coverage, findings, counterevidence and open questions. Use successive waves if needed; without agents, use separate manageable passes. The lead owns a coverage record and checks that the entire agreed portfolio has a result or an explicit unassessed status.
Reconcile inconsistent interpretations across reviewers before comparing projects. Trace portfolio-level tensions that individual reviews can miss—for example, several projects whose combined resource demands crowd out a stated commitment. Support that conclusion with actual allocations and dependencies rather than treating every project as equally costly.
5. Work through tensions and propose changes
Show the most consequential supported findings first. For each tension, describe the project choice, the values involved, evidence, possible consequences and practical alternatives. Where values conflict, explain the tradeoff and ask for my judgment; do not invent a universal hierarchy or decide it silently. Use existing guidance where it actually resolves the case.
Propose changes at the level the evidence supports: alter a requirement, change an incentive, add a missing stakeholder input, revise resource allocation, change a project approach or reconsider whether to continue it. Explain which value each change would serve, what it would cost or displace, and what must be clarified before choosing it. Keep recommendations separate from my decisions and leave ownership unassigned unless established.
Have an independent reviewer inspect the report, accepted interpretations and necessary evidence for inconsistent standards, unsupported motives and missed counterevidence where possible. Otherwise use a separate review pass and disclose shared context. Repair material findings.
6. Deliver the portfolio review
Provide the official values alongside the agreed working interpretations; a dated inventory with assessed and unassessed projects; project-level findings with sources; examples of demonstrated alignment; consequential tensions; and concrete proposed changes. Keep unknowns distinct from misalignment. Summarize the few decisions that need my attention and the evidence that would resolve remaining uncertainty.
Review the result with me and incorporate corrections. If I choose actions, record those choices accurately. Deliver the completed assessment and proposals without modifying project systems, policies or budgets or contacting colleagues unless separately requested.
Done when
You have an evidence-based review of the agreed portfolio against explicit working interpretations of the firm's values, including supported alignment, concrete tensions, proposed changes and visible gaps in coverage.
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.