Designing for Moments of Need

Use an outcome-first structure. Give ChatGPT the role, goal, approved source notes, constraints, and exact output you want back.

I am using Build The System for L&D systems work.

Prompt: Designing for Moments of Need

Goal: Create 30-second, 3-minute, and 10-minute support for a real work task.

Audience: L&D teams replacing overbuilt courses with support closer to the work.

Source material I will provide:
- Task
- Where people get stuck
- Available source material
- Tool or workflow context

Inputs to use: [task], [failure point], [source material], [workflow context]

Working notes:
- task: [add task]
- failure point: [add failure point]
- source material: [add source material]
- workflow context: [add workflow context]

Rules:
- Use only approved source material.
- Do not invent policy, compliance, learner, employee, customer, financial, or business facts.
- Do not paste sensitive, confidential, employee, learner, customer, or proprietary data into an AI tool unless your organization has approved that tool for that data.
- Treat AI output as a draft that needs human review.

Return:
1. 30-second support
2. 3-minute support
3. 10-minute support
4. Where each version should live

Human review checklist:
- Does the output stay inside the source material?
- Are assumptions and missing information labeled?
- Is there a clear human owner for the final decision?
- Does the output need legal, compliance, privacy, accessibility, leader, requester, or SME review?

Use labeled sections so context, source material, task, constraints, and output format stay separate.

<context>
I am using Build The System for L&D systems work.
Prompt: Designing for Moments of Need
Use case: Create 30-second, 3-minute, and 10-minute support for a real work task.
Audience: L&D teams replacing overbuilt courses with support closer to the work.
</context>

<source_material_to_prepare>
- Task
- Where people get stuck
- Available source material
- Tool or workflow context
</source_material_to_prepare>

<inputs>
- task: [add task]
- failure point: [add failure point]
- source material: [add source material]
- workflow context: [add workflow context]
</inputs>

<task>
Use the source material and inputs to produce a practical, review-ready output for this L&D workflow. Stay inside the source material. If a detail is missing, mark it as "Needs confirmation" instead of inventing it.
</task>

<constraints>
- Use only approved source material.
- Do not invent policy, compliance, learner, employee, customer, financial, or business facts.
- Do not paste sensitive, confidential, employee, learner, customer, or proprietary data into an AI tool unless your organization has approved that tool for that data.
- Treat AI output as a draft that needs human review.
</constraints>

<output_format>
1. 30-second support
2. 3-minute support
3. 10-minute support
4. Where each version should live
</output_format>

<human_review>
- Does the output stay inside the source material?
- Are assumptions and missing information labeled?
- Is there a clear human owner for the final decision?
- Does the output need legal, compliance, privacy, accessibility, leader, requester, or SME review?
</human_review>

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

Goal: Help me complete Designing for Moments of Need for an L&D workflow.

Source: Use only the selected Microsoft 365 document, meeting notes, email thread, spreadsheet, SharePoint file, or pasted notes I provide. Do not use unsupported assumptions.

Context:
- Use case: Create 30-second, 3-minute, and 10-minute support for a real work task.
- Audience: L&D teams replacing overbuilt courses with support closer to the work.
- Source material to have ready:
- Task
- Where people get stuck
- Available source material
- Tool or workflow context

Inputs:
- task: [add task]
- failure point: [add failure point]
- source material: [add source material]
- workflow context: [add workflow context]

Expectations:
- Use only approved source material.
- Do not invent policy, compliance, learner, employee, customer, financial, or business facts.
- Do not paste sensitive, confidential, employee, learner, customer, or proprietary data into an AI tool unless your organization has approved that tool for that data.
- Treat AI output as a draft that needs human review.

Output:
1. 30-second support
2. 3-minute support
3. 10-minute support
4. Where each version should live

Before finalizing, add a short "Needs human review" section covering:
- Does the output stay inside the source material?
- Are assumptions and missing information labeled?
- Is there a clear human owner for the final decision?
- Does the output need legal, compliance, privacy, accessibility, leader, requester, or SME review?

Use a task-first structure with clear input labels, one example pattern, rules, and a concise output format. For Obsidian context, use approved excerpts, Drive exports, Google Docs, or NotebookLM source sets.

Task: Complete Designing for Moments of Need for an L&D workflow.

Use case:
Create 30-second, 3-minute, and 10-minute support for a real work task.

Audience:
L&D teams replacing overbuilt courses with support closer to the work.

Input labels to use:
- task: [add task]
- failure point: [add failure point]
- source material: [add source material]
- workflow context: [add workflow context]

Source material to prepare:
- Task
- Where people get stuck
- Available source material
- Tool or workflow context

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

Rules:
- Use only approved source material.
- Do not invent policy, compliance, learner, employee, customer, financial, or business facts.
- Do not paste sensitive, confidential, employee, learner, customer, or proprietary data into an AI tool unless your organization has approved that tool for that data.
- Treat AI output as a draft that needs human review.

Return:
1. 30-second support
2. 3-minute support
3. 10-minute support
4. Where each version should live

Human review checklist:
- Does the output stay inside the source material?
- Are assumptions and missing information labeled?
- Is there a clear human owner for the final decision?
- Does the output need legal, compliance, privacy, accessibility, leader, requester, or SME review?