Diagnostic

Name the L&D system problem before choosing the fix.

Use this quick check when the team knows something is stuck but does not know whether the useful move is intake, SME review, content maintenance, LMS governance, measurement, AI workflow design, manager support, or clearer ownership.

Start the diagnostic Use Start Here
How to use this

This is a triage tool, not a scorecard.

Answer with the current reality. The result gives you one place to inspect and one practical move to try before adding another course, tool, dashboard, or AI workflow.

Manual first

Use the result to guide one conversation, whiteboard map, checklist, or request review.

Make it visible

Use the workspace move when the team needs a shared artifact in Microsoft 365 or Google Workspace.

Use AI carefully

Use AI to draft, sort, summarize, or stress-test the work. Keep a human responsible for facts, risk, and final decisions.

Answer the current state

Where is the system weakest right now?

Choose the answer that best matches how the work actually runs today.

Intake clarity

Requests arrive as courses, workshops, or assets before the team has named the work problem.

When a training request comes in, can the team name the audience, task, workflow, and evidence before work starts?
Can requesters explain what someone should do differently after the support exists?
SME review quality

Review comments mix facts, preferences, workflow changes, risk issues, and approval calls.

Can reviewers tell the difference between a fact issue, workflow issue, preference, approval issue, and risk issue?
Does every review cycle have a named decision owner and a clear rule for reopening scope?
Content maintainability

The library is growing, but ownership, review dates, reuse, and retirement rules are hard to see.

Can the team name which content is current, owned, used, duplicated, or ready to retire?
Can a broad course be traced back to the role-based tasks people actually need to perform?
LMS governance

Reports, permissions, catalog structure, migrations, and admin rules keep turning into one-off decisions.

Can the team explain who owns repeated LMS decisions about reports, permissions, catalog structure, and admin rules?
Can LMS reports answer the decisions leaders actually need to make?
Measurement credibility

The team can show completions, but not readiness, behavior, adoption, manager feedback, or workflow impact.

Can the team name the decision the measurement evidence needs to support?
Can the team show evidence beyond completions, satisfaction, or attendance?
AI workflow maturity

People are using AI, but source material, allowed tasks, review gates, and owners are unclear.

Is AI assigned to a defined workflow step, or is it being used as a side experiment?
Can the team name what AI may use, what it may not do, who reviews the output, and who owns the final decision?
Manager and learner support

The training exists, but support at the point of work, manager follow-up, and practice signals are weak.

Can learners find support at the moment they need to do the task?
Do managers know what to observe, reinforce, or coach after the learning experience?
Operational ownership

The work depends on memory, heroics, and side conversations because ownership and status are unclear.

Can the team see who owns intake, review, publishing, maintenance, reporting, and governance decisions?
Can someone tell whether work is proposed, accepted, blocked, in review, published, maintained, or retired?
All possible outcomes

Use these when you already recognize the problem.

Each outcome points to a topic, field note, example, template, and glossary terms so you can move without reading the whole site.

Intake clarity

The team is accepting a format before it has enough information to choose the right response.

  • InspectPull the last five requests and look for the moment when the team first named the task, audience, workflow, and evidence.
  • StartUse the Training Intake Worksheet on one live request before accepting the format.
Prompt starters for this outcome

ChatGPT GPT-5 family

Use an outcome-first prompt with the job, approved source material, constraints, and the exact artifact you want back.

I am working on Your intake is doing too much too late. for an L&D system problem.

Goal: Help me turn the notes below into a practical next move.

Context: Requests show up as course titles, workshops, or assets. The real task, audience, workflow break, and evidence standard get discovered after work has already started.

Use these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.

Rules:
- Use only the source notes I provide.
- Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
- Separate known facts, assumptions, missing information, and next actions.
- Flag anything that needs requester, reviewer, leader, legal, compliance, LMS owner, or manager confirmation.
- Keep the output practical enough to review in a working meeting.

Source notes:
[paste approved notes here]

Return:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Claude 4 family

Use XML-style sections so context, source material, task, constraints, and output format stay separate.

<context>
I am working on Your intake is doing too much too late. for an L&D system problem.
Requests show up as course titles, workshops, or assets. The real task, audience, workflow break, and evidence standard get discovered after work has already started.
</context>

<source_notes>
[paste approved notes here]
</source_notes>

<task>
Turn the source notes into a practical next move using these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
</task>

<constraints>
Use only the source notes provided.
Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
Separate known facts, assumptions, missing information, risks, and next actions.
Flag anything that changes scope, ownership, evidence, risk, or decision rights.
</constraints>

<output_format>
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action
</output_format>

Gemini 3 family

Use a clear task, labeled input, and one example pattern. For Obsidian context, use approved excerpts, Drive exports, Google Docs, or NotebookLM source sets.

Task: Help me make progress on Your intake is doing too much too late. from the notes provided.

Context: Requests show up as course titles, workshops, or assets. The real task, audience, workflow break, and evidence standard get discovered after work has already started.

Working fields:
- what is known
- what is assumed
- what is missing
- what to inspect
- manual move
- workspace move
- AI-assisted move

Example pattern:
Field: Missing information
Good answer: Name the specific information to confirm, who can confirm it, and why it affects the next decision.

Rules:
- Use only the source notes provided.
- If information is missing, write "Needs confirmation".
- Keep the output concise and reviewable.
- End with the next best action.

Source notes:
[paste approved notes here]

Output format:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Microsoft 365 Copilot

Use goal, context, source, expectations, and output. For Obsidian context, use approved excerpts, Word summaries, OneDrive files, SharePoint pages, Teams context, or Outlook threads.

Goal: Help me make progress on Your intake is doing too much too late..

Context: Requests show up as course titles, workshops, or assets. The real task, audience, workflow break, and evidence standard get discovered after work has already started.

Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.

Expectations:
- Work with these fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
- Mark uncertain items as "Needs confirmation".
- Do not add facts that are not in the source.
- Separate known facts, assumptions, missing information, risks, and next actions.
- Summarize the top review questions for the team.

Output:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

SME review quality

Every kind of feedback is landing in the same review step, so review becomes slow and hard to close.

  • InspectTake one recent review thread and label every comment by feedback type before responding.
  • StartUse the SME Review Checklist on one review cycle and close comments by category.
Prompt starters for this outcome

ChatGPT GPT-5 family

Use an outcome-first prompt with the job, approved source material, constraints, and the exact artifact you want back.

I am working on Your SME review is acting like a catch-all approval system. for an L&D system problem.

Goal: Help me turn the notes below into a practical next move.

Context: A reviewer fixes wording, changes workflow, catches risk, reopens priority, and approves accuracy in the same comment thread.

Use these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.

Rules:
- Use only the source notes I provide.
- Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
- Separate known facts, assumptions, missing information, and next actions.
- Flag anything that needs requester, reviewer, leader, legal, compliance, LMS owner, or manager confirmation.
- Keep the output practical enough to review in a working meeting.

Source notes:
[paste approved notes here]

Return:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Claude 4 family

Use XML-style sections so context, source material, task, constraints, and output format stay separate.

<context>
I am working on Your SME review is acting like a catch-all approval system. for an L&D system problem.
A reviewer fixes wording, changes workflow, catches risk, reopens priority, and approves accuracy in the same comment thread.
</context>

<source_notes>
[paste approved notes here]
</source_notes>

<task>
Turn the source notes into a practical next move using these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
</task>

<constraints>
Use only the source notes provided.
Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
Separate known facts, assumptions, missing information, risks, and next actions.
Flag anything that changes scope, ownership, evidence, risk, or decision rights.
</constraints>

<output_format>
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action
</output_format>

Gemini 3 family

Use a clear task, labeled input, and one example pattern. For Obsidian context, use approved excerpts, Drive exports, Google Docs, or NotebookLM source sets.

Task: Help me make progress on Your SME review is acting like a catch-all approval system. from the notes provided.

Context: A reviewer fixes wording, changes workflow, catches risk, reopens priority, and approves accuracy in the same comment thread.

Working fields:
- what is known
- what is assumed
- what is missing
- what to inspect
- manual move
- workspace move
- AI-assisted move

Example pattern:
Field: Missing information
Good answer: Name the specific information to confirm, who can confirm it, and why it affects the next decision.

Rules:
- Use only the source notes provided.
- If information is missing, write "Needs confirmation".
- Keep the output concise and reviewable.
- End with the next best action.

Source notes:
[paste approved notes here]

Output format:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Microsoft 365 Copilot

Use goal, context, source, expectations, and output. For Obsidian context, use approved excerpts, Word summaries, OneDrive files, SharePoint pages, Teams context, or Outlook threads.

Goal: Help me make progress on Your SME review is acting like a catch-all approval system..

Context: A reviewer fixes wording, changes workflow, catches risk, reopens priority, and approves accuracy in the same comment thread.

Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.

Expectations:
- Work with these fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
- Mark uncertain items as "Needs confirmation".
- Do not add facts that are not in the source.
- Separate known facts, assumptions, missing information, risks, and next actions.
- Summarize the top review questions for the team.

Output:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Content maintainability

Content is being created faster than the team can maintain, reuse, update, or retire it.

  • InspectChoose one high-use content area and add owner, task, audience, source, last review date, and retirement trigger.
  • StartUse the Content Maintenance Tracker on one content area before starting another rebuild.
Prompt starters for this outcome

ChatGPT GPT-5 family

Use an outcome-first prompt with the job, approved source material, constraints, and the exact artifact you want back.

I am working on Your content library needs an operating layer. for an L&D system problem.

Goal: Help me turn the notes below into a practical next move.

Context: Courses stay live because nobody owns retirement. People rebuild assets because they cannot tell what already exists or whether it is safe to reuse.

Use these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.

Rules:
- Use only the source notes I provide.
- Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
- Separate known facts, assumptions, missing information, and next actions.
- Flag anything that needs requester, reviewer, leader, legal, compliance, LMS owner, or manager confirmation.
- Keep the output practical enough to review in a working meeting.

Source notes:
[paste approved notes here]

Return:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Claude 4 family

Use XML-style sections so context, source material, task, constraints, and output format stay separate.

<context>
I am working on Your content library needs an operating layer. for an L&D system problem.
Courses stay live because nobody owns retirement. People rebuild assets because they cannot tell what already exists or whether it is safe to reuse.
</context>

<source_notes>
[paste approved notes here]
</source_notes>

<task>
Turn the source notes into a practical next move using these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
</task>

<constraints>
Use only the source notes provided.
Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
Separate known facts, assumptions, missing information, risks, and next actions.
Flag anything that changes scope, ownership, evidence, risk, or decision rights.
</constraints>

<output_format>
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action
</output_format>

Gemini 3 family

Use a clear task, labeled input, and one example pattern. For Obsidian context, use approved excerpts, Drive exports, Google Docs, or NotebookLM source sets.

Task: Help me make progress on Your content library needs an operating layer. from the notes provided.

Context: Courses stay live because nobody owns retirement. People rebuild assets because they cannot tell what already exists or whether it is safe to reuse.

Working fields:
- what is known
- what is assumed
- what is missing
- what to inspect
- manual move
- workspace move
- AI-assisted move

Example pattern:
Field: Missing information
Good answer: Name the specific information to confirm, who can confirm it, and why it affects the next decision.

Rules:
- Use only the source notes provided.
- If information is missing, write "Needs confirmation".
- Keep the output concise and reviewable.
- End with the next best action.

Source notes:
[paste approved notes here]

Output format:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Microsoft 365 Copilot

Use goal, context, source, expectations, and output. For Obsidian context, use approved excerpts, Word summaries, OneDrive files, SharePoint pages, Teams context, or Outlook threads.

Goal: Help me make progress on Your content library needs an operating layer..

Context: Courses stay live because nobody owns retirement. People rebuild assets because they cannot tell what already exists or whether it is safe to reuse.

Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.

Expectations:
- Work with these fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
- Mark uncertain items as "Needs confirmation".
- Do not add facts that are not in the source.
- Separate known facts, assumptions, missing information, risks, and next actions.
- Summarize the top review questions for the team.

Output:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

LMS governance

Platform work is being handled request by request instead of through visible governance decisions.

  • InspectList the five LMS decisions your team repeats most often and name the current rule, owner, and review trigger.
  • StartUse the LMS Governance Decision Log for the next repeated LMS question.
Prompt starters for this outcome

ChatGPT GPT-5 family

Use an outcome-first prompt with the job, approved source material, constraints, and the exact artifact you want back.

I am working on Your LMS needs clearer decision rules. for an L&D system problem.

Goal: Help me turn the notes below into a practical next move.

Context: The same report, permission, catalog, or migration question comes back because the owner, rule, and decision history are not visible.

Use these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.

Rules:
- Use only the source notes I provide.
- Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
- Separate known facts, assumptions, missing information, and next actions.
- Flag anything that needs requester, reviewer, leader, legal, compliance, LMS owner, or manager confirmation.
- Keep the output practical enough to review in a working meeting.

Source notes:
[paste approved notes here]

Return:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Claude 4 family

Use XML-style sections so context, source material, task, constraints, and output format stay separate.

<context>
I am working on Your LMS needs clearer decision rules. for an L&D system problem.
The same report, permission, catalog, or migration question comes back because the owner, rule, and decision history are not visible.
</context>

<source_notes>
[paste approved notes here]
</source_notes>

<task>
Turn the source notes into a practical next move using these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
</task>

<constraints>
Use only the source notes provided.
Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
Separate known facts, assumptions, missing information, risks, and next actions.
Flag anything that changes scope, ownership, evidence, risk, or decision rights.
</constraints>

<output_format>
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action
</output_format>

Gemini 3 family

Use a clear task, labeled input, and one example pattern. For Obsidian context, use approved excerpts, Drive exports, Google Docs, or NotebookLM source sets.

Task: Help me make progress on Your LMS needs clearer decision rules. from the notes provided.

Context: The same report, permission, catalog, or migration question comes back because the owner, rule, and decision history are not visible.

Working fields:
- what is known
- what is assumed
- what is missing
- what to inspect
- manual move
- workspace move
- AI-assisted move

Example pattern:
Field: Missing information
Good answer: Name the specific information to confirm, who can confirm it, and why it affects the next decision.

Rules:
- Use only the source notes provided.
- If information is missing, write "Needs confirmation".
- Keep the output concise and reviewable.
- End with the next best action.

Source notes:
[paste approved notes here]

Output format:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Microsoft 365 Copilot

Use goal, context, source, expectations, and output. For Obsidian context, use approved excerpts, Word summaries, OneDrive files, SharePoint pages, Teams context, or Outlook threads.

Goal: Help me make progress on Your LMS needs clearer decision rules..

Context: The same report, permission, catalog, or migration question comes back because the owner, rule, and decision history are not visible.

Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.

Expectations:
- Work with these fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
- Mark uncertain items as "Needs confirmation".
- Do not add facts that are not in the source.
- Separate known facts, assumptions, missing information, risks, and next actions.
- Summarize the top review questions for the team.

Output:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Measurement credibility

The team is starting with available data instead of the decision the evidence needs to support.

  • InspectName one decision the evidence should support and one behavior signal that would make that decision more credible.
  • StartUse the Measurement Planning Worksheet before adding another report.
Prompt starters for this outcome

ChatGPT GPT-5 family

Use an outcome-first prompt with the job, approved source material, constraints, and the exact artifact you want back.

I am working on Your measurement needs a decision before it needs another dashboard. for an L&D system problem.

Goal: Help me turn the notes below into a practical next move.

Context: Leaders ask whether training worked. The team shows completions, satisfaction, or dashboard activity, but cannot connect the data to readiness, behavior, adoption, or workflow impact.

Use these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.

Rules:
- Use only the source notes I provide.
- Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
- Separate known facts, assumptions, missing information, and next actions.
- Flag anything that needs requester, reviewer, leader, legal, compliance, LMS owner, or manager confirmation.
- Keep the output practical enough to review in a working meeting.

Source notes:
[paste approved notes here]

Return:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Claude 4 family

Use XML-style sections so context, source material, task, constraints, and output format stay separate.

<context>
I am working on Your measurement needs a decision before it needs another dashboard. for an L&D system problem.
Leaders ask whether training worked. The team shows completions, satisfaction, or dashboard activity, but cannot connect the data to readiness, behavior, adoption, or workflow impact.
</context>

<source_notes>
[paste approved notes here]
</source_notes>

<task>
Turn the source notes into a practical next move using these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
</task>

<constraints>
Use only the source notes provided.
Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
Separate known facts, assumptions, missing information, risks, and next actions.
Flag anything that changes scope, ownership, evidence, risk, or decision rights.
</constraints>

<output_format>
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action
</output_format>

Gemini 3 family

Use a clear task, labeled input, and one example pattern. For Obsidian context, use approved excerpts, Drive exports, Google Docs, or NotebookLM source sets.

Task: Help me make progress on Your measurement needs a decision before it needs another dashboard. from the notes provided.

Context: Leaders ask whether training worked. The team shows completions, satisfaction, or dashboard activity, but cannot connect the data to readiness, behavior, adoption, or workflow impact.

Working fields:
- what is known
- what is assumed
- what is missing
- what to inspect
- manual move
- workspace move
- AI-assisted move

Example pattern:
Field: Missing information
Good answer: Name the specific information to confirm, who can confirm it, and why it affects the next decision.

Rules:
- Use only the source notes provided.
- If information is missing, write "Needs confirmation".
- Keep the output concise and reviewable.
- End with the next best action.

Source notes:
[paste approved notes here]

Output format:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Microsoft 365 Copilot

Use goal, context, source, expectations, and output. For Obsidian context, use approved excerpts, Word summaries, OneDrive files, SharePoint pages, Teams context, or Outlook threads.

Goal: Help me make progress on Your measurement needs a decision before it needs another dashboard..

Context: Leaders ask whether training worked. The team shows completions, satisfaction, or dashboard activity, but cannot connect the data to readiness, behavior, adoption, or workflow impact.

Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.

Expectations:
- Work with these fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
- Mark uncertain items as "Needs confirmation".
- Do not add facts that are not in the source.
- Separate known facts, assumptions, missing information, risks, and next actions.
- Summarize the top review questions for the team.

Output:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

AI workflow maturity

The team has access to AI before it has agreed on source material, allowed tasks, review gates, and human ownership.

  • InspectChoose one AI use case and name the source material, allowed AI task, not-allowed task, review gate, and human owner.
  • StartUse the AI Workflow Brief before adding AI to another L&D task.
Prompt starters for this outcome

ChatGPT GPT-5 family

Use an outcome-first prompt with the job, approved source material, constraints, and the exact artifact you want back.

I am working on Your AI use needs a workflow boundary. for an L&D system problem.

Goal: Help me turn the notes below into a practical next move.

Context: People try prompts in isolation. Outputs move into learning work without a clear source check, SME check, accessibility check, or risk review.

Use these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.

Rules:
- Use only the source notes I provide.
- Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
- Separate known facts, assumptions, missing information, and next actions.
- Flag anything that needs requester, reviewer, leader, legal, compliance, LMS owner, or manager confirmation.
- Keep the output practical enough to review in a working meeting.

Source notes:
[paste approved notes here]

Return:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Claude 4 family

Use XML-style sections so context, source material, task, constraints, and output format stay separate.

<context>
I am working on Your AI use needs a workflow boundary. for an L&D system problem.
People try prompts in isolation. Outputs move into learning work without a clear source check, SME check, accessibility check, or risk review.
</context>

<source_notes>
[paste approved notes here]
</source_notes>

<task>
Turn the source notes into a practical next move using these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
</task>

<constraints>
Use only the source notes provided.
Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
Separate known facts, assumptions, missing information, risks, and next actions.
Flag anything that changes scope, ownership, evidence, risk, or decision rights.
</constraints>

<output_format>
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action
</output_format>

Gemini 3 family

Use a clear task, labeled input, and one example pattern. For Obsidian context, use approved excerpts, Drive exports, Google Docs, or NotebookLM source sets.

Task: Help me make progress on Your AI use needs a workflow boundary. from the notes provided.

Context: People try prompts in isolation. Outputs move into learning work without a clear source check, SME check, accessibility check, or risk review.

Working fields:
- what is known
- what is assumed
- what is missing
- what to inspect
- manual move
- workspace move
- AI-assisted move

Example pattern:
Field: Missing information
Good answer: Name the specific information to confirm, who can confirm it, and why it affects the next decision.

Rules:
- Use only the source notes provided.
- If information is missing, write "Needs confirmation".
- Keep the output concise and reviewable.
- End with the next best action.

Source notes:
[paste approved notes here]

Output format:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Microsoft 365 Copilot

Use goal, context, source, expectations, and output. For Obsidian context, use approved excerpts, Word summaries, OneDrive files, SharePoint pages, Teams context, or Outlook threads.

Goal: Help me make progress on Your AI use needs a workflow boundary..

Context: People try prompts in isolation. Outputs move into learning work without a clear source check, SME check, accessibility check, or risk review.

Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.

Expectations:
- Work with these fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
- Mark uncertain items as "Needs confirmation".
- Do not add facts that are not in the source.
- Separate known facts, assumptions, missing information, risks, and next actions.
- Summarize the top review questions for the team.

Output:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Manager and learner support

The learning asset exists, but the surrounding manager, job aid, practice, and point-of-work support are thin.

  • InspectPick one task and list the moment of need, job aid, manager observation, practice check, and follow-up question.
  • StartChoose one task and add a job aid plus one manager observation question.
Prompt starters for this outcome

ChatGPT GPT-5 family

Use an outcome-first prompt with the job, approved source material, constraints, and the exact artifact you want back.

I am working on Your learning support stops too early. for an L&D system problem.

Goal: Help me turn the notes below into a practical next move.

Context: People complete training but still ask the same questions in the workflow. Managers do not know what good looks like or what to coach.

Use these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.

Rules:
- Use only the source notes I provide.
- Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
- Separate known facts, assumptions, missing information, and next actions.
- Flag anything that needs requester, reviewer, leader, legal, compliance, LMS owner, or manager confirmation.
- Keep the output practical enough to review in a working meeting.

Source notes:
[paste approved notes here]

Return:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Claude 4 family

Use XML-style sections so context, source material, task, constraints, and output format stay separate.

<context>
I am working on Your learning support stops too early. for an L&D system problem.
People complete training but still ask the same questions in the workflow. Managers do not know what good looks like or what to coach.
</context>

<source_notes>
[paste approved notes here]
</source_notes>

<task>
Turn the source notes into a practical next move using these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
</task>

<constraints>
Use only the source notes provided.
Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
Separate known facts, assumptions, missing information, risks, and next actions.
Flag anything that changes scope, ownership, evidence, risk, or decision rights.
</constraints>

<output_format>
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action
</output_format>

Gemini 3 family

Use a clear task, labeled input, and one example pattern. For Obsidian context, use approved excerpts, Drive exports, Google Docs, or NotebookLM source sets.

Task: Help me make progress on Your learning support stops too early. from the notes provided.

Context: People complete training but still ask the same questions in the workflow. Managers do not know what good looks like or what to coach.

Working fields:
- what is known
- what is assumed
- what is missing
- what to inspect
- manual move
- workspace move
- AI-assisted move

Example pattern:
Field: Missing information
Good answer: Name the specific information to confirm, who can confirm it, and why it affects the next decision.

Rules:
- Use only the source notes provided.
- If information is missing, write "Needs confirmation".
- Keep the output concise and reviewable.
- End with the next best action.

Source notes:
[paste approved notes here]

Output format:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Microsoft 365 Copilot

Use goal, context, source, expectations, and output. For Obsidian context, use approved excerpts, Word summaries, OneDrive files, SharePoint pages, Teams context, or Outlook threads.

Goal: Help me make progress on Your learning support stops too early..

Context: People complete training but still ask the same questions in the workflow. Managers do not know what good looks like or what to coach.

Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.

Expectations:
- Work with these fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
- Mark uncertain items as "Needs confirmation".
- Do not add facts that are not in the source.
- Separate known facts, assumptions, missing information, risks, and next actions.
- Summarize the top review questions for the team.

Output:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Operational ownership

The work is moving through people, not through a clear system of owners, statuses, decision rights, and review habits.

  • InspectMap one workflow from request to publish and name the owner, status, decision point, and handoff at each step.
  • StartCreate one owner-status map before adding another workflow tool.
Prompt starters for this outcome

ChatGPT GPT-5 family

Use an outcome-first prompt with the job, approved source material, constraints, and the exact artifact you want back.

I am working on Your operating model needs visible ownership. for an L&D system problem.

Goal: Help me turn the notes below into a practical next move.

Context: Progress depends on who remembers the history. Decisions sit in meetings, chats, tickets, and inboxes instead of a shared operating layer.

Use these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.

Rules:
- Use only the source notes I provide.
- Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
- Separate known facts, assumptions, missing information, and next actions.
- Flag anything that needs requester, reviewer, leader, legal, compliance, LMS owner, or manager confirmation.
- Keep the output practical enough to review in a working meeting.

Source notes:
[paste approved notes here]

Return:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Claude 4 family

Use XML-style sections so context, source material, task, constraints, and output format stay separate.

<context>
I am working on Your operating model needs visible ownership. for an L&D system problem.
Progress depends on who remembers the history. Decisions sit in meetings, chats, tickets, and inboxes instead of a shared operating layer.
</context>

<source_notes>
[paste approved notes here]
</source_notes>

<task>
Turn the source notes into a practical next move using these working fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
</task>

<constraints>
Use only the source notes provided.
Do not invent policy details, metrics, learner needs, compliance requirements, or business context.
Separate known facts, assumptions, missing information, risks, and next actions.
Flag anything that changes scope, ownership, evidence, risk, or decision rights.
</constraints>

<output_format>
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action
</output_format>

Gemini 3 family

Use a clear task, labeled input, and one example pattern. For Obsidian context, use approved excerpts, Drive exports, Google Docs, or NotebookLM source sets.

Task: Help me make progress on Your operating model needs visible ownership. from the notes provided.

Context: Progress depends on who remembers the history. Decisions sit in meetings, chats, tickets, and inboxes instead of a shared operating layer.

Working fields:
- what is known
- what is assumed
- what is missing
- what to inspect
- manual move
- workspace move
- AI-assisted move

Example pattern:
Field: Missing information
Good answer: Name the specific information to confirm, who can confirm it, and why it affects the next decision.

Rules:
- Use only the source notes provided.
- If information is missing, write "Needs confirmation".
- Keep the output concise and reviewable.
- End with the next best action.

Source notes:
[paste approved notes here]

Output format:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action

Microsoft 365 Copilot

Use goal, context, source, expectations, and output. For Obsidian context, use approved excerpts, Word summaries, OneDrive files, SharePoint pages, Teams context, or Outlook threads.

Goal: Help me make progress on Your operating model needs visible ownership..

Context: Progress depends on who remembers the history. Decisions sit in meetings, chats, tickets, and inboxes instead of a shared operating layer.

Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.

Expectations:
- Work with these fields: what is known, what is assumed, what is missing, what to inspect, manual move, workspace move, AI-assisted move.
- Mark uncertain items as "Needs confirmation".
- Do not add facts that are not in the source.
- Separate known facts, assumptions, missing information, risks, and next actions.
- Summarize the top review questions for the team.

Output:
1. Likely problem pattern
2. Known facts
3. Assumptions
4. Missing information
5. Risks to review
6. Recommended next action