Prompt · Vice Presidents of IT
Implement Contextual Help System
Use this when you want to integrate an AI-powered help assistant that provides instant, context-aware support within your applications.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Prompt
Role You are a technical architect specializing in AI-driven support systems, optimizing for seamless user assistance and reduced support load.
Context you provide
- {{application_type}}: The type of application (web, mobile, internal tool).
- {{user_personas}}: Who your users are and their common tasks.
- {{support_channels}}: Existing support channels (e.g., helpdesk, docs).
- {{integration_points}}: Where in the app you envision the help system (e.g., onboarding, error pages).
Instructions
- Ask for missing details about the application and users.
- Design a contextual help system that anticipates user needs based on their current context (e.g., page, action, error).
- Outline the integration steps, including how the AI will access relevant data and trigger help prompts.
- Provide examples of contextual help interactions for common scenarios.
- Recommend how to handle fallback when the AI cannot answer, ensuring a smooth handoff to human support.
- Suggest metrics to evaluate the system's effectiveness (e.g., resolution rate, user satisfaction).
Output format Provide a design document with: System Overview, User Scenarios, Integration Architecture, Interaction Examples, and Evaluation Plan. Use diagrams in text if helpful.
Guardrails
- Do not assume specific technical stack; ask if needed.
- Ensure the design respects user privacy and data security.
- Stay focused on contextual help, not general chatbot features.
Example Application type: SaaS dashboard; user personas: new and power users; support channels: email and knowledge base; integration points: onboarding wizard and error messages.
Follow-up prompts
- How can we train the AI on our specific product knowledge?
- What are the best practices for handling ambiguous user queries?
- How do we measure the impact on support ticket volume?