The purpose of this article is to explain the value, workflow, and configuration requirements of the Solution Design Expert AI Agent, a digital assistant tailored to help users build manufacturing solutions on the Tulip platform. This agent is designed to ensure users develop correct, lean, and maintainable applications by guiding them through best practices in planning, data modeling, and resource re-use.
AI Agents in Tulip
Start with the AI Agents in Tulip Library article to learn the basics before using this tool.
Overview
The Solution Design Expert AI Agent acts as a virtual Tulip consultant, helping users to plan, review existing resources, and design manufacturing applications while adhering strictly to user requests and Tulip best practices. The agent’s main goal is to guide users to the minimal viable solution, ensuring composable app architecture, optimal data modeling, and prevention of unnecessary duplication.
Value & Use Cases
The Solution Design Expert AI Agent provides expertise at every step of the manufacturing app design process, driving higher quality, faster deployments, and long-term maintainability. Below are typical use cases:
| Use Case | Description | Value | Target User | Example Prompt |
|---|---|---|---|---|
| Solution Planning | Guiding users through feature planning and minimal viable product design | Reduces overengineering, saves time | Manufacturing Engineers | "How should I structure my work order tracking app?" |
| Data Model Evaluation | Reviewing existing tables/resources before creating new assets | Prevents duplication, ensures consistent reporting | Solution Architects | "Which tables should I reuse for defect tracking?" |
| App Wireframe Design | Mapping the flow and structure of new manufacturing apps using Tulip UI/UX best practices | Accelerates prototyping, improves operator adoption | App Builders | "Can you suggest a wireframe for material receiving?" |
| Library Asset Recommendation | Pointing users to relevant, reusable assets from Tulip Library | Promotes re-use, speeds up solution delivery | All Users | "Is there an inspection app template I can re-use?" |
| Change Impact Assessment | Asking clarifying questions to ensure deep understanding before any changes are proposed or applied | Reduces rework and errors | IT/Process Managers | "Should I edit the 'Units' table or create a new one?" |
Agent configuration
(Agent ready to use) In order to use this agent, simply import it into your Tulip instance. The prompt and tools will be pre-configured, and no additional setup is necessary.
How to Prompt AI Agents Effectively in Tulip
A well-crafted prompt is essential when working with Tulip’s AI Agents. The quality and precision of your prompt directly impact the relevance, accuracy, and usefulness of the agent’s response.
General Guidance
- Be specific: State exactly what you want the agent to do. If you are seeking planning, say so. If you want to analyze a specific problem or process, describe it concisely.
- Reference existing resources: If you know the names of apps, tables, or connectors, mention them. This helps the agent search and reuse rather than rebuild.
- Set boundaries: If you have constraints, like “do not change table schema” or “only suggest, do not build”, make them clear in your prompt.
- Tell the agent about your users/personas: The more you share about who will use a feature (e.g., “forklift operators” vs. “quality techs”), the better the tailored advice.
- Describe the process step-by-step: If you’re mapping a process, write the sequence or decisions clearly.
Prompting Do’s and Don’ts
| Do | Don’t |
|---|---|
| Clearly state what solution, process, or challenge you’re facing | Use vague prompts like “help me with production” |
| List any relevant existing assets (tables, apps) | Ask for “something similar to…” without giving specifics |
| Mention key constraints (user roles, devices, compliance needs) | Leave out requirements or user context |
| Ask clear questions about planning and scoping | Request a build before confirming what’s already available in your instance |
| Request a review (“Can you check if a defect tracking table exists?”) | Assume the agent knows your data model without telling it (unless it just analyzed it) |
| Break complex requests into steps | Try to solve multiple, unrelated problems in one prompt |
| Use examples if possible for the desired outcome | Allow the agent to assume missing details without asking for clarification |
Sample Effective Prompts
Planning:
- “I want to track machine downtime events. Can you check if I have a table for downtime logs and recommend the minimum changes needed to track both planned and unplanned downtimes?”
Resource Review:
- “Before building a new app for quality inspections, can you list existing tables or apps related to inspections in my instance?”
Wireframe/UI:
- “Can you suggest a simple two-step workflow for operators to record incoming material in Tulip, using mobile devices?”
Constraint-Specific:
- “Suggest a solution for defect tracking, but do not make any schema changes to the ‘Units’ or ‘Defects’ tables.”
What to Avoid
- Don’t use generic prompts like “help me with my process.”
- Don’t leave out process details or existing tools.
- Don’t instruct the agent to create new things without first checking for existing ones.
- Don’t request multiple major features in a single, unfocused prompt.
Conclusion
The Solution Design Expert AI Agent streamlines your journey from idea to working solution, enforcing rigorous scoping, data model discipline, and best practices. By prioritizing review, planning, and clarification, this agent helps you avoid duplication, keep apps maintainable, and accelerate time-to-value in your digital factory.