Hire for promise. Let AI fill technical gaps.
Someone might have the curiosity, initiative and imagination you want while lacking the conventional résumé for the role. Could AI supply enough technical support to let that person thrive? This activity takes a real job apart, investigates that possibility and explores what you could hire for if some familiar requirements changed.
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
- Unpacks a job description—or your rough account of the job—to find what its technical, experience and educational requirements are meant to accomplish.
- Investigates where AI might fill those gaps, tries representative work where possible, and develops ways to hire for qualities such as creativity, agency and curiosity.
What to have ready
- A job description, an old posting or a loose spoken or written download of the work.
- Any accessible examples of the job, previous role discussions and the tools a new hire could actually use.
Where you come in
- Clarify what excellent work looks like and which human qualities you most want to hire for.
- Review the proposed support and choose a hiring approach worth trying.
What you'll get
An evidence-based account of which requirements might change with AI support, alternative ways to hire for promise, and a draft role and hiring exercise for the approach you choose.
You're done when
You can explain which conventional requirements might change, what AI support would make that possible, what remains to be tested and how your chosen hiring approach would reveal the human qualities you need.
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. ### Understand the job before changing its requirements Help me explore hiring for promise: whether AI could augment a person with less conventional training or experience by filling particular technical gaps, allowing us to hire for other qualities such as creativity, agency or curiosity. Treat that as a possibility to investigate for this job, not a conclusion. Work on role and hiring-process design; do not evaluate, score or select actual applicants. Accept a job description, past posting, rough notes or a loose spoken account. Use its terminology, team and projects to inspect available connections and search relevant hiring-manager emails, team chats and other messages, role-planning meeting transcripts, job descriptions, work samples, project records and onboarding materials. Find what the person really does, where work becomes difficult, what good results look like and why past requirements were included. Prefer descriptions of the work over personal records about individual employees. Check what AI tools and relevant knowledge sources a new hire would actually be allowed and able to use. Search internal tool guidance, approved-access documents and team experience with those tools. Do this investigation before asking me to reconstruct information you can access. If access is unavailable, investigate setup and permissible exports, then ask for the smallest useful input. Explain what remains tentative when we have only my description. Summarize the job's intended outcomes and recurring or consequential tasks. Ask a focused question about any missing fact that changes the analysis, one at a time. Confirm the role you are examining before redesigning it. ### Find what each requirement is doing Extract the conventional technical skills, years or kinds of experience, educational requirements and credentials. For each, connect it to the actual task or judgment it is meant to support. Separate documented reasons from your hypotheses. An old degree requirement may stand for knowledge, practice, a credential or simply a convention; do not assume which. Break the work into concrete examples: interpreting a report, assembling an analysis, using a specialized system, noticing an unusual case, explaining a recommendation or deciding when to ask an expert. Identify the knowledge, tool operation, judgment and verification each example requires. Preserve requirements that have a documented mandatory purpose; identify the source and ask the owner to resolve uncertainty rather than silently rewriting them. ### Investigate how AI could support a less experienced person For each promising gap, describe a specific support mechanism: an assistant grounded in approved reference material, a guided workflow, code or analysis assistance, explanations at the moment of need, worked examples or checks by an experienced colleague. Explain what the person still has to understand, notice and decide. Identify the sources, tools, training and expert availability that make the proposal plausible. Inspect actual available tools and verify changeable capability claims against current primary documentation. Where the environment permits, construct the proposed support for a small set of representative tasks using suitable sample work. Run those tasks, compare the output with known good work or an expert's criteria, and record both successes and failures. Include a case requiring the user to recognize uncertainty or a misleading answer. An AI completing a task itself does not establish that a novice can use it successfully; state exactly what each trial shows. If a capability cannot be tried, mark it as untested. For a large role, give agents bounded task families and common requirements for sources, proposed support, remaining human ability and trial evidence. Have a separate reviewer inspect the actual task outputs and role requirements. Reconcile disagreements and preserve gaps in coverage. Without agents, use manageable sequential passes and disclose when review shares context. Produce a requirements map showing what appears to remain essential on entry, what might be learned with AI support, and what might become less important if the support is validated. Explain the evidence behind each judgment and what a human trial would need to establish. Do not convert a promising demo into proof that experience or education is unnecessary. ### Explore ways to hire for promise Use that map to develop materially different hiring approaches suited to the job. Possibilities include emphasizing a narrower core of required expertise while using AI for adjacent technical work; hiring for learning ability with a structured apprenticeship and AI support; or opening the role to people from another field whose creativity, agency or curiosity fits its purpose. These are starting points—derive the approaches from this job. For each approach, describe the work the person would own, the qualities to seek, the technical baseline, the AI support, the onboarding and available human supervision. Define qualities behaviorally: for example, curiosity might show up as asking a question that exposes a missing assumption, while agency might show up as finding and testing a next step without a complete brief. Avoid vague personality labels or substituting “culture fit” for job-relevant evidence. Show what changes in the posting and what a realistic hiring exercise would reveal. An exercise might give everyone the same tools and task, ask them to improve an initial answer, introduce a surprise and ask them to explain what they would check. Explain which observations support each desired quality, and what the exercise cannot establish. Recommend an approach on the evidence, then ask me to choose or amend it before producing the final hiring materials. ### Draft the chosen role and a practical trial Write the revised job description, a concise explanation of changed and retained requirements, and a hiring exercise with consistent instructions and observable job-related assessment criteria. Make the promised AI support explicit so the role does not depend on tools that no one has supplied. Add an onboarding outline linking the support to actual early work. Specify a small trial with willing participants, if needed, that compares representative task performance with the proposed support against the job's success criteria. Include output quality, recognition of mistakes, ability to explain decisions, time and help needed. Draft the materials; do not recruit people, process actual applications or publish the posting without a separate request. Deliver the requirements map, evidence and open questions, the alternative approaches and the selected hiring materials. Identify which changes are ready to discuss and which still depend on a successful human trial. Stop with a usable proposal for this role. 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
Hire for promise. Let AI fill technical gaps.
What the AI will do
- Unpacks a job description—or your rough account of the job—to find what its technical, experience and educational requirements are meant to accomplish.
- Investigates where AI might fill those gaps, tries representative work where possible, and develops ways to hire for qualities such as creativity, agency and curiosity.
What you can provide
- A job description, an old posting or a loose spoken or written download of the work.
- Any accessible examples of the job, previous role discussions and the tools a new hire could actually use.
Where you'll take part
- Clarify what excellent work looks like and which human qualities you most want to hire for.
- Review the proposed support and choose a hiring approach worth trying.
What you'll get
An evidence-based account of which requirements might change with AI support, alternative ways to hire for promise, and a draft role and hiring exercise for the approach you choose.
Activity context
Someone might have the curiosity, initiative and imagination you want while lacking the conventional résumé for the role. Could AI supply enough technical support to let that person thrive? This activity takes a real job apart, investigates that possibility and explores what you could hire for if some familiar requirements changed.
For the user
Bring a job description or just talk through what the person would do. The AI will find relevant role and work records, investigate possible AI support, and develop concrete hiring approaches. You will help define success, choose the qualities that matter and review the resulting role and exercise.
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
Understand the job before changing its requirements
Help me explore hiring for promise: whether AI could augment a person with less conventional training or experience by filling particular technical gaps, allowing us to hire for other qualities such as creativity, agency or curiosity. Treat that as a possibility to investigate for this job, not a conclusion. Work on role and hiring-process design; do not evaluate, score or select actual applicants.
Accept a job description, past posting, rough notes or a loose spoken account. Use its terminology, team and projects to inspect available connections and search relevant hiring-manager emails, team chats and other messages, role-planning meeting transcripts, job descriptions, work samples, project records and onboarding materials. Find what the person really does, where work becomes difficult, what good results look like and why past requirements were included. Prefer descriptions of the work over personal records about individual employees.
Check what AI tools and relevant knowledge sources a new hire would actually be allowed and able to use. Search internal tool guidance, approved-access documents and team experience with those tools. Do this investigation before asking me to reconstruct information you can access. If access is unavailable, investigate setup and permissible exports, then ask for the smallest useful input. Explain what remains tentative when we have only my description.
Summarize the job's intended outcomes and recurring or consequential tasks. Ask a focused question about any missing fact that changes the analysis, one at a time. Confirm the role you are examining before redesigning it.
Find what each requirement is doing
Extract the conventional technical skills, years or kinds of experience, educational requirements and credentials. For each, connect it to the actual task or judgment it is meant to support. Separate documented reasons from your hypotheses. An old degree requirement may stand for knowledge, practice, a credential or simply a convention; do not assume which.
Break the work into concrete examples: interpreting a report, assembling an analysis, using a specialized system, noticing an unusual case, explaining a recommendation or deciding when to ask an expert. Identify the knowledge, tool operation, judgment and verification each example requires. Preserve requirements that have a documented mandatory purpose; identify the source and ask the owner to resolve uncertainty rather than silently rewriting them.
Investigate how AI could support a less experienced person
For each promising gap, describe a specific support mechanism: an assistant grounded in approved reference material, a guided workflow, code or analysis assistance, explanations at the moment of need, worked examples or checks by an experienced colleague. Explain what the person still has to understand, notice and decide. Identify the sources, tools, training and expert availability that make the proposal plausible.
Inspect actual available tools and verify changeable capability claims against current primary documentation. Where the environment permits, construct the proposed support for a small set of representative tasks using suitable sample work. Run those tasks, compare the output with known good work or an expert's criteria, and record both successes and failures. Include a case requiring the user to recognize uncertainty or a misleading answer. An AI completing a task itself does not establish that a novice can use it successfully; state exactly what each trial shows. If a capability cannot be tried, mark it as untested.
For a large role, give agents bounded task families and common requirements for sources, proposed support, remaining human ability and trial evidence. Have a separate reviewer inspect the actual task outputs and role requirements. Reconcile disagreements and preserve gaps in coverage. Without agents, use manageable sequential passes and disclose when review shares context.
Produce a requirements map showing what appears to remain essential on entry, what might be learned with AI support, and what might become less important if the support is validated. Explain the evidence behind each judgment and what a human trial would need to establish. Do not convert a promising demo into proof that experience or education is unnecessary.
Explore ways to hire for promise
Use that map to develop materially different hiring approaches suited to the job. Possibilities include emphasizing a narrower core of required expertise while using AI for adjacent technical work; hiring for learning ability with a structured apprenticeship and AI support; or opening the role to people from another field whose creativity, agency or curiosity fits its purpose. These are starting points—derive the approaches from this job.
For each approach, describe the work the person would own, the qualities to seek, the technical baseline, the AI support, the onboarding and available human supervision. Define qualities behaviorally: for example, curiosity might show up as asking a question that exposes a missing assumption, while agency might show up as finding and testing a next step without a complete brief. Avoid vague personality labels or substituting “culture fit” for job-relevant evidence.
Show what changes in the posting and what a realistic hiring exercise would reveal. An exercise might give everyone the same tools and task, ask them to improve an initial answer, introduce a surprise and ask them to explain what they would check. Explain which observations support each desired quality, and what the exercise cannot establish. Recommend an approach on the evidence, then ask me to choose or amend it before producing the final hiring materials.
Draft the chosen role and a practical trial
Write the revised job description, a concise explanation of changed and retained requirements, and a hiring exercise with consistent instructions and observable job-related assessment criteria. Make the promised AI support explicit so the role does not depend on tools that no one has supplied. Add an onboarding outline linking the support to actual early work.
Specify a small trial with willing participants, if needed, that compares representative task performance with the proposed support against the job's success criteria. Include output quality, recognition of mistakes, ability to explain decisions, time and help needed. Draft the materials; do not recruit people, process actual applications or publish the posting without a separate request.
Deliver the requirements map, evidence and open questions, the alternative approaches and the selected hiring materials. Identify which changes are ready to discuss and which still depend on a successful human trial. Stop with a usable proposal for this role.
Done when
You can explain which conventional requirements might change, what AI support would make that possible, what remains to be tested and how your chosen hiring approach would reveal the human qualities you need.
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.