For a long time, product teams relied on long written documents to define what should be built. Requirements, rules, and flows were described in detail in an attempt to predict every possible decision upfront. The problem is simple: products do not come to life in documents. They come to life through interaction.

Today, prototypes are no longer just visual artifacts used at the end of the design process. They are becoming a central thinking tool. A well crafted prototype can explain intent, expose risks, align teams, and replace large portions of traditional product documentation.

When a prototype is clear, it removes ambiguity. Instead of debating abstract descriptions, teams react to something tangible. The conversation shifts from what should happen to what is actually happening. This change raises the quality of discussions and accelerates decision making.

Prototypes also transform collaboration. Designers, product managers, engineers, and stakeholders can interact with the same source of truth. Everyone can test ideas, challenge assumptions, and suggest improvements based on a shared experience rather than interpretations of text.

Another key advantage is early user feedback. Interactive prototypes allow teams to validate behavior before investing in full development. Even incomplete flows generate insights that are far more reliable than assumptions written in a document.

Documentation still matters, but its role changes. Instead of being the starting point, it becomes a support layer. The experience leads, and documentation explains what is not immediately visible.

One of the biggest challenges, however, is starting. A blank canvas can be intimidating. This is where tools like Figma Make can help designers and product thinkers move faster by turning intent into something concrete.

Below is a simple prompt model you can use in Figma Make to break the blank canvas and start exploring ideas.

Figma Make prompt example

Copy and adapt the prompt below based on your context:

“Create an interactive prototype for a digital product focused on solving a real user problem.
The target user is [describe the user].
The main problem to solve is [describe the problem].

Start with a simple core flow that includes:
• An entry point screen
• A primary action
• A feedback or confirmation state

Focus on clarity over visual polish.
Use realistic copy and basic layout structure.
Assume this prototype will be used to discuss behavior and decisions with stakeholders, not final visuals.”

This type of prompt helps transform abstract ideas into something testable. Instead of staring at an empty frame, you start with intent, behavior, and flow. From there, refinement becomes much easier.

Using prototypes as a thinking tool is not about skipping process. It is about shifting where clarity is created. When teams can see, test, and interact with ideas early, they make better decisions and build better products.

If you treat prototypes as living artifacts rather than static deliverables, the blank canvas stops being a blocker and becomes an opportunity.

Here at Zup, StackSpot AI has been one of those transformative tools, especially for those working in complex contexts.

In this article, you will discover how StackSpot AI has enhanced my work as a product designer in the project I am part of, bringing more speed, accuracy, and innovation to the development of solutions.

What is StackSpot AI?
StackSpot AI is a multi-agent platform created to be used throughout the software development lifecycle. Its flexibility allows it to be adapted to the needs of different business areas.

For designers, it becomes a powerful ally, offering resources that go beyond technical development, helping to structure processes, organize information, generate insights, and even improve communication.

AI for design: how StackSpot AI transformed my routine
In the project I am part of, I used StackSpot AI to automate tasks that previously required a lot of energy and time. The most important change was the increase in intelligence within the design process, enabling more efficient and user-centered solutions.

Below, you can check the main resources that were developed and the real impacts achieved in practice.

Customized agents
I created customized AI agents to meet the specific needs of the product design team. I configured these agents to understand the context of the industry I work in, using Knowledge Sources to ensure that the generated solutions were contextualized around the challenges we face.

The Expert Designer Agent

The Expert Designer Agent was created to operate across product design fronts within a specific industry.

This agent was configured to understand the industry context, interpreting data and helping to develop solutions that truly make sense for that market.

The agent also acts as a support tool, offering valuable insights and data-driven recommendations about common practices, market trends, and similar products.

Integrated with a specialized knowledge base, it helps designers structure processes, organize information, and improve communication with stakeholders. This ensures that the solutions developed are effective and aligned with the needs of the industry.

Alt text: Image of the documentation showing the screen for creating and configuring an AI agent within StackSpot AI.

Specialized knowledge base
I structured a robust and industry-specific database. This base brings together up-to-date and reliable information, delivering an essential benefit: more speed with safety.

Before, I had to search for data across multiple sources and compare different versions, which took time. Now, with everything centralized, I have traceability and access control, which speeds up my work and reduces the risk of failures in strategic design decisions.

Alt text: Image of the documentation showing where to configure the StackSpot AI knowledge base.

Quick Command for UX Writing
In addition, I also created a Quick Command (QC) for UX Writing specific to the industry, a feature that makes text reviews easier.

By using the QC, I can ensure clearer, more consistent communication aligned with client guidelines, promoting agility in content production and greater accuracy in messaging.

The Quick Command was especially useful for creating messages that follow the tone of voice used by clients. Instead of manually reviewing everything, I can now ensure that the content is well-written, in the right tone, and within expectations much faster.

Alt text: Image of the StackSpot AI Quick Command configuration showing the writing review step.

Results achieved
The integration of StackSpot AI into our routine brought tangible benefits, going far beyond task automation. Check out the main results:

• More agility in processes: we significantly reduced the time spent on operational tasks such as searching for information and reviewing texts. This allowed the team to focus on what really matters: creating strategic solutions for clients.
• More strategy, less operation: with AI handling repetitive tasks, we were able to dedicate more energy to data analysis, product planning, and innovation.
• More accuracy and insights: StackSpot AI increased the precision of decisions and provided valuable insights for product development. For example, we were able to identify customer behavior patterns that previously went unnoticed.

Reflections on using StackSpot AI
The greatest benefit I gained from StackSpot AI was not just efficiency, but clarity.

With fewer operational tasks, I was able to direct my energy toward what really matters: planning, analysis, strategy, and decisions that move the product forward.

StackSpot AI did not come to replace designers, but to increase our capacity to think, decide, and create more impact.

Tips for designers who want to adopt StackSpot AI
If you are a designer thinking about using StackSpot AI, here are some AI-for-design tips:

• Understand your needs: before implementing any solution, be clear about the challenges you face daily. This will help you configure the tool more efficiently.
• Customize the resources: StackSpot AI allows you to create custom agents and commands. Use this flexibility to adapt the tool to your context.
• Show value to the team: the tool only delivers results if the team trusts it. Make presentations, demonstrate it in practice, co-create solutions, and work closely with your team.
• Track results: monitor the impact of the tool on your routine and stay open-minded about making adjustments. AI learns from you, and you learn from it.

AI for design: more speed and depth
Using AI for design with StackSpot AI transformed my routine as a product designer.

With the platform, I was able to move out of operational mode and start working with more vision, speed, and depth. I also gained more time to focus on what matters most: making strategic decisions and being more precise in the solutions.

If you also believe in the power of technology to enhance creative work, I recommend exploring StackSpot AI and other AI tools. After all, the future of our work lies in using tools that expand and scale our capabilities.

Take advantage and create your free trial account on StackSpot AI. Just log in with your Google or GitHub account.

The key point is this: writing good prompts is not a trick. It is a communication and design skill that transforms implicit knowledge into clear instructions for machines. Just like writing a requirement or defining a hypothesis, well-crafted prompts describe intent, context, expected behavior, and constraints.

1. Prompts as a Tool for Clear Communication

One of the biggest wins for designers using AI is communication. Drafting messages, adapting tone for different audiences, and translating technical language into simple explanations all become faster and more consistent.

Examples

• Rewrite a difficult email to sound clear, professional, and collaborative.
• Turn vague stakeholder feedback into concrete design guidance.
• Explain a technical concept to a non-technical audience.

Why this matters: clear communication reduces rework and helps cross-functional teams move forward with fewer misunderstandings.

2. Product Thinking Supported by AI

Beyond writing, AI can support strategic thinking. Designers can use it to explore alternative perspectives, simulate user feedback with personas, or review decisions based on usability principles.

Examples

• Review this interface using common UX heuristics.
• Imagine you are this type of user. How would you react to this screen?
• Act as a UX mentor and suggest approaches for this leadership challenge.

This works like a second brain for quick reflection, critique, and ideation.

3. AI in Visual Production and Prototyping with Figma Make

ChatGPT and tools like Figma Make work well together. While ChatGPT helps structure language, logic, and reasoning, Figma Make interprets prompts to generate visual components, layouts, and interactive prototypes.

The main difference is the type of prompt and the level of detail required.

Based on real designer workflows:

1. PRD-based prompts
   Use detailed descriptions of what to build, how it should behave, and which constraints apply. This leads to more consistent and usable prototypes.
2. Assisted prompt generation
   Start with a rough idea and let the system structure it into a complete prompt. This is useful for quick exploration.
3. The TOKEN framework
   Task, Output, Key elements, Expected behavior, Notable constraints.
   This framework helps ensure your prompt contains all critical elements before sending it.

4. An Integrated Flow from Idea to Prototype

Step 1.
Explore with ChatGPT

Use structured prompts to think about the problem, challenge assumptions, clarify requirements, and turn vague ideas into clear instructions.

Step 2.
Translate into a Figma Make prompt

Convert these requirements into a format that defines task, output, UI elements, expected behavior, and constraints.

Step 3.
Iterate between human and AI

Generate early prototypes, refine them in Figma, and adjust your prompts based on what you learn from each output.

5. Best Practices for Writing Effective Prompts

To get real value from AI in design, keep these principles in mind:

A. Provide context and purpose
Without context, AI will make generic assumptions. Always explain where this screen or feature fits and why it exists.

B. Describe expected behavior
Do not just say “create a dashboard.” Explain how elements should react, update, or interact.

C. Add constraints and style rules
Mention platform, accessibility needs, design system rules, or brand guidelines when relevant.

D. Reduce ambiguity
A good prompt does not hide uncertainty. It exposes it and resolves it.