Training intake is treated like a form instead of a decision system.
Good intake helps the team decide whether to build training, improve documentation, fix a workflow, support managers, adjust the tool, or gather better evidence before creating another asset.
Make the system visible before making it bigger.
Collect the last five requests
Pull five recent requests and write the requested format, audience, task, workflow break, requester, and current status.
Sort request types
Sort each request into training, documentation, workflow, manager support, tool issue, measurement issue, or needs discovery.
Define the minimum intake questions
Choose the smallest set of questions needed before accepting the work: audience, task, workflow break, evidence, owner, and decision.
Test with one requester
Use the questions on one live request and note where the conversation gets clearer, stuck, or too heavy.
Set the repeatable rhythm
Decide how requests enter, who triages them, what statuses mean, and when a request is accepted, redirected, blocked, or sent back for more detail.
Pick the lightest system that makes the work repeatable.
Use a whiteboard or one-page worksheet to map the request, audience, task, workflow break, evidence, owner, status, and decision.
Use Forms plus Lists, Forms plus Excel, Google Forms plus Sheets, or a shared project board to capture intake fields and make status visible.
Use AI to sort rough request notes, draft clarifying questions, identify likely non-training causes, and summarize what still needs human confirmation.
Use these words when intake needs to slow down without stalling.
- Before we choose a format, I want to make sure we understand the work problem.
- What should the audience be able to do that they cannot reliably do now?
- Where does that task break in the real workflow?
- What evidence would make us comfortable saying the support helped?
- Based on this, we may build training, but we may also redirect to documentation, manager support, workflow cleanup, a tool fix, or a measurement step.
Use intake to choose the next move.
The audience, task, workflow break, evidence, owner, and review path are clear enough to start.
The issue is better solved through documentation, manager support, workflow cleanup, tool support, or communication.
The requester has not confirmed the task, audience, evidence, or decision owner.
The team needs examples, performance data, support tickets, manager input, or learner feedback before choosing a solution.
Look for operating signals, not just activity.
- Percent of requests with task, audience, workflow break, and evidence named before acceptance.
- Number of requests redirected away from unnecessary course production.
- Average time from request to first decision.
- Most common missing intake field.
- Requester feedback on whether the conversation clarified the need.
Use the sources as thinking tools, not a script.
Useful for framing training requests as signals from a larger work system instead of treating the requested asset as the answer.
Supports the idea that a job aid, checklist, or workflow support can be a better response than a course when help is needed at the moment of work.
Use AI to prepare, inspect, and summarize the intake work.
Diagnose a messy request
The requester has named a training format before the work problem is clear.
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 Diagnose a messy request for an L&D system problem.
Goal: Help me turn the notes below into a practical next move.
Context: The requester has named a training format before the work problem is clear.
Use these working fields: request, audience, task, workflow break, evidence, owner, decision.
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 request type
2. Known facts
3. Assumptions
4. Missing information
5. Clarifying questions
6. Recommended next move Claude 4 family
Use XML-style sections so context, source material, task, constraints, and output format stay separate.
<context>
I am working on Diagnose a messy request for an L&D system problem.
The requester has named a training format before the work problem is clear.
</context>
<source_notes>
[paste approved notes here]
</source_notes>
<task>
Turn the source notes into a practical next move using these working fields: request, audience, task, workflow break, evidence, owner, decision.
</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 request type
2. Known facts
3. Assumptions
4. Missing information
5. Clarifying questions
6. Recommended next move
</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 Diagnose a messy request from the notes provided.
Context: The requester has named a training format before the work problem is clear.
Working fields:
- request
- audience
- task
- workflow break
- evidence
- owner
- decision
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 request type
2. Known facts
3. Assumptions
4. Missing information
5. Clarifying questions
6. Recommended next move 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 Diagnose a messy request.
Context: The requester has named a training format before the work problem is clear.
Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.
Expectations:
- Work with these fields: request, audience, task, workflow break, evidence, owner, decision.
- 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 request type
2. Known facts
3. Assumptions
4. Missing information
5. Clarifying questions
6. Recommended next move Turn rough notes into intake questions
The team has notes from a requester conversation and needs better follow-up questions.
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 Turn rough notes into intake questions for an L&D system problem.
Goal: Help me turn the notes below into a practical next move.
Context: The team has notes from a requester conversation and needs better follow-up questions.
Use these working fields: request, audience, task, workflow break, evidence, owner, decision.
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. Draft intake summary
2. Questions to ask the requester
3. Questions to ask the manager or workflow owner
4. Risks to check
5. 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 Turn rough notes into intake questions for an L&D system problem.
The team has notes from a requester conversation and needs better follow-up questions.
</context>
<source_notes>
[paste approved notes here]
</source_notes>
<task>
Turn the source notes into a practical next move using these working fields: request, audience, task, workflow break, evidence, owner, decision.
</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. Draft intake summary
2. Questions to ask the requester
3. Questions to ask the manager or workflow owner
4. Risks to check
5. 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 Turn rough notes into intake questions from the notes provided.
Context: The team has notes from a requester conversation and needs better follow-up questions.
Working fields:
- request
- audience
- task
- workflow break
- evidence
- owner
- decision
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. Draft intake summary
2. Questions to ask the requester
3. Questions to ask the manager or workflow owner
4. Risks to check
5. 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 Turn rough notes into intake questions.
Context: The team has notes from a requester conversation and needs better follow-up questions.
Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.
Expectations:
- Work with these fields: request, audience, task, workflow break, evidence, owner, decision.
- 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. Draft intake summary
2. Questions to ask the requester
3. Questions to ask the manager or workflow owner
4. Risks to check
5. Next action Sort requests by type
The team has several requests and needs to sort them before accepting work.
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 Sort requests by type for an L&D system problem.
Goal: Help me turn the notes below into a practical next move.
Context: The team has several requests and needs to sort them before accepting work.
Use these working fields: request, audience, task, workflow break, evidence, owner, decision.
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. Request category
2. Reason for category
3. Missing information
4. Suggested owner
5. 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 Sort requests by type for an L&D system problem.
The team has several requests and needs to sort them before accepting work.
</context>
<source_notes>
[paste approved notes here]
</source_notes>
<task>
Turn the source notes into a practical next move using these working fields: request, audience, task, workflow break, evidence, owner, decision.
</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. Request category
2. Reason for category
3. Missing information
4. Suggested owner
5. 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 Sort requests by type from the notes provided.
Context: The team has several requests and needs to sort them before accepting work.
Working fields:
- request
- audience
- task
- workflow break
- evidence
- owner
- decision
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. Request category
2. Reason for category
3. Missing information
4. Suggested owner
5. 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 Sort requests by type.
Context: The team has several requests and needs to sort them before accepting work.
Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.
Expectations:
- Work with these fields: request, audience, task, workflow break, evidence, owner, decision.
- 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. Request category
2. Reason for category
3. Missing information
4. Suggested owner
5. Next action Identify missing information
The team is about to accept work and needs to confirm whether the scope is ready.
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 Identify missing information for an L&D system problem.
Goal: Help me turn the notes below into a practical next move.
Context: The team is about to accept work and needs to confirm whether the scope is ready.
Use these working fields: request, audience, task, workflow break, evidence, owner, decision.
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. Ready to accept
2. Needs confirmation
3. Risks
4. Decision owner
5. Recommended response Claude 4 family
Use XML-style sections so context, source material, task, constraints, and output format stay separate.
<context>
I am working on Identify missing information for an L&D system problem.
The team is about to accept work and needs to confirm whether the scope is ready.
</context>
<source_notes>
[paste approved notes here]
</source_notes>
<task>
Turn the source notes into a practical next move using these working fields: request, audience, task, workflow break, evidence, owner, decision.
</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. Ready to accept
2. Needs confirmation
3. Risks
4. Decision owner
5. Recommended response
</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 Identify missing information from the notes provided.
Context: The team is about to accept work and needs to confirm whether the scope is ready.
Working fields:
- request
- audience
- task
- workflow break
- evidence
- owner
- decision
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. Ready to accept
2. Needs confirmation
3. Risks
4. Decision owner
5. Recommended response 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 Identify missing information.
Context: The team is about to accept work and needs to confirm whether the scope is ready.
Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.
Expectations:
- Work with these fields: request, audience, task, workflow break, evidence, owner, decision.
- 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. Ready to accept
2. Needs confirmation
3. Risks
4. Decision owner
5. Recommended response Draft a requester follow-up
The team needs a practical follow-up message that clarifies the request without sounding bureaucratic.
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 Draft a requester follow-up for an L&D system problem.
Goal: Help me turn the notes below into a practical next move.
Context: The team needs a practical follow-up message that clarifies the request without sounding bureaucratic.
Use these working fields: request, audience, task, workflow break, evidence, owner, decision.
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. Short response
2. Questions to answer
3. Why these questions matter
4. Suggested next meeting or decision Claude 4 family
Use XML-style sections so context, source material, task, constraints, and output format stay separate.
<context>
I am working on Draft a requester follow-up for an L&D system problem.
The team needs a practical follow-up message that clarifies the request without sounding bureaucratic.
</context>
<source_notes>
[paste approved notes here]
</source_notes>
<task>
Turn the source notes into a practical next move using these working fields: request, audience, task, workflow break, evidence, owner, decision.
</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. Short response
2. Questions to answer
3. Why these questions matter
4. Suggested next meeting or decision
</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 Draft a requester follow-up from the notes provided.
Context: The team needs a practical follow-up message that clarifies the request without sounding bureaucratic.
Working fields:
- request
- audience
- task
- workflow break
- evidence
- owner
- decision
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. Short response
2. Questions to answer
3. Why these questions matter
4. Suggested next meeting or decision 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 Draft a requester follow-up.
Context: The team needs a practical follow-up message that clarifies the request without sounding bureaucratic.
Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.
Expectations:
- Work with these fields: request, audience, task, workflow break, evidence, owner, decision.
- 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. Short response
2. Questions to answer
3. Why these questions matter
4. Suggested next meeting or decision Review the intake workflow for risk
The team wants to make the intake process useful without making it heavy.
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 Review the intake workflow for risk for an L&D system problem.
Goal: Help me turn the notes below into a practical next move.
Context: The team wants to make the intake process useful without making it heavy.
Use these working fields: request, audience, task, workflow break, evidence, owner, decision.
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. What works
2. What is too heavy
3. What is missing
4. Risks
5. One simplification Claude 4 family
Use XML-style sections so context, source material, task, constraints, and output format stay separate.
<context>
I am working on Review the intake workflow for risk for an L&D system problem.
The team wants to make the intake process useful without making it heavy.
</context>
<source_notes>
[paste approved notes here]
</source_notes>
<task>
Turn the source notes into a practical next move using these working fields: request, audience, task, workflow break, evidence, owner, decision.
</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. What works
2. What is too heavy
3. What is missing
4. Risks
5. One simplification
</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 Review the intake workflow for risk from the notes provided.
Context: The team wants to make the intake process useful without making it heavy.
Working fields:
- request
- audience
- task
- workflow break
- evidence
- owner
- decision
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. What works
2. What is too heavy
3. What is missing
4. Risks
5. One simplification 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 Review the intake workflow for risk.
Context: The team wants to make the intake process useful without making it heavy.
Source: Use the selected document, meeting notes, spreadsheet, email thread, SharePoint file, or pasted notes as the only source.
Expectations:
- Work with these fields: request, audience, task, workflow break, evidence, owner, decision.
- 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. What works
2. What is too heavy
3. What is missing
4. Risks
5. One simplification Run the Day 1 request sort with five recent requests before changing the intake form.