In the first part of this series, we explored how AI can support product design through learning, idea generation, and user research. In this second part, we'll cover three more ways AI can refine your process — focusing on design systems, collaboration, and product strategy. The goal in each case is the same: stay in control, use AI as a partner, and keep human judgment at the center of every decision.

4. Design System Refinement

Design system creation is time-consuming. You're making careful decisions, working from brand colors or inherited brand guides, standard type scales, and a wide range of usage contexts. The work often involves tedious, repetitive tasks: populating tokens, organizing styles, scaling values across a consistent naming system.

AI can assist with the repetitive parts — but you're still the one making the decisions. AI doesn't have taste, and it doesn't understand the context and human nuance behind a brand. You still need to guide the process. Think of it as having a very fast assistant who can execute on your direction precisely, as long as you've been precise in giving it.

One technique worth knowing: the meta-prompt. Instead of asking for an immediate answer, a meta-prompt asks AI to first generate a detailed prompt for you — a higher-level instruction that co-creates the structure of your request so you get more tailored, powerful results.

Example prompts to try

Refine this brand color palette for a cohesive and balanced visual system using a harmonious color scheme (complementary, analogous, or split-complementary). Create system colors (error, success, warning, info, background, text) that are distinct yet cohesive. Provide hex codes and clear, human-readable names for each. [paste brand colors]

Using a modular ratio of [1.25], create a scalable type system for a digital product using [font name] with 4 heading sizes and 2 paragraph sizes. Use a consistent naming convention (like fontSizeHeading1). Calculate REM values based on a base font size of 16px, and suggest line heights for accessibility. Present the result as a table with token name, pixel size, REM value, and recommended line height.

5. Designing for Collaboration

As a design project grows, assets accumulate and files become harder to navigate. Keeping everything organized — and providing clear guidance to developers during implementation — is its own discipline. AI can help by offering structured advice on categorizing and documenting your assets.

While AI can't directly interact with your design tools, you can describe your setup and get specific recommendations on how to organize files, name components, and structure your Figma document for handoff. By delegating the organizational thinking to AI, you free up mental bandwidth for the design decisions that actually require your judgment.

Example prompts to try

Explain how atomic design relates to how design assets are organized, specifically in the context of forms and form fields.

Explain how using the BEM naming convention can help organize Figma design assets and create a smoother designer-to-developer handoff.

The result is a design system that functions as a collaborative, well-documented asset — one that supports efficient workflows rather than creating friction for the people building from it.

6. Product Strategy

Developing a robust product strategy is essential, but organizing the raw output from workshops and user interviews can be overwhelming. Stickies, notes, screenshots, and affinity clusters accumulate quickly. AI can act as a second set of eyes — sorting through unstructured data to create logical themes and groupings.

In practice, this looks like sharing screenshots of sticky note boards or pasting raw interview notes and asking AI to group them by similarity, then cluster those groups into broader themes. The AI doesn't replace your interpretation, but it dramatically reduces the time spent on the mechanical sorting work — so you can get to synthesis faster.

Example prompts to try

I have a collection of sticky note insights from a user research workshop. Each note contains a short statement from a participant. Please: (1) organize them into rows or groups by similarity to identify how many times a topic was mentioned, and (2) cluster these groups into broader themes (e.g., pain points, communication issues, technical issues). [paste notes]

Take a look at this customer profile in the Value Proposition Canvas. Based on the customer jobs, pains, and gains provided, suggest ideas for the left side of the canvas: features, services, and solutions that could create strong product-market fit. Ensure suggestions are relevant to the design context and directly address the noted pain points and goals of the user group.

Take the following product feature suggestions [paste/add file] and organize them into an impact/effort matrix. Each feature should be placed in one of four quadrants: Quick Wins (high impact, low effort), Major Projects (high impact, high effort), For a Rainy Day (low impact, low effort), and Time Wasters (low impact, high effort). Provide a clear explanation for why each feature belongs in that quadrant.

Across all three areas — design systems, collaboration, and strategy — the pattern is the same. AI accelerates the foundational work so you can focus on the bigger picture. It lightens the load of managing early-stage data, organizing assets, and scaling visual systems. It can't replace human intuition, but it can clear the path for it.