AI In Design Thinking

To understand why prompt wording matters, it helps to know what brainstorming was trying to solve in the first place. In the mid-20th century, brainstorming popularized a rule that sounds almost quaint now: separate the generation of ideas from the evaluation of ideas. The intent was psychological. When evaluation happens too early - when you start judging an idea before it has fully taken shape - people clamp down. They become cautious. They produce fewer ideas and spend more time polishing the safe ones.

But anyone who has run a real brainstorming session knows the other problem: after a while, people repeat themselves. The room runs out of fresh angles not because creativity disappears, but because attention gets sticky. You keep circling the same concept, the same category, the same “kind” of thought. That’s where AI enters - not as a replacement for thinking, but as a way to keep the search moving when your own mental search starts to loop.

The Spark Ladder Prompt Method is built around a specific design tension: idea volume should increase, but the “direction” of those ideas should keep you climbing toward something. The method treats prompts like rungs, not like a single instruction. Instead of asking for a massive list in one go, the prompt sequence nudges the AI toward producing ideas that are meaningfully different from one another, then gradually narrows attention toward constraints that matter in your problem space.

That’s the key to the chapter’s topic: it’s not just that AI can generate lots of ideas. It’s that prompts can create a ladder structure - wider at the top, more focused as you go - so you don’t end up with a pile of near-duplicates. A prompt can also protect momentum by reducing the “blank page” pause. Humans often get stuck at the moment where they can’t tell what kind of idea would count as progress. A well-shaped prompt gives the mind a foothold, and the mind keeps moving.

The surprising part is that “more” is not automatically “better.” If an AI prompt is too open-ended, the model may respond by averaging toward common patterns - the design equivalent of saying, “Tell me what you think,” and getting back a safe summary. If a prompt is too narrow too early, you get novelty that doesn’t connect to the actual problem. The Spark Ladder Prompt Method aims to stay between those extremes: increase variety without erasing the thread that ties the ideas to one coherent design direction.

When Brainstorming Meets Prediction: Why AI Can Either Widen Search or Flatten Taste

AI doesn’t brainstorm the way a person does. A person has a memory of past experiences, a sense of taste, and an internal model of what feels plausible. AI, at least in its common chat-style form, produces text by predicting what comes next based on patterns in its training data. That matters for creativity because it means the AI is sensitive to the shape of your request.

There’s a specific failure mode that designers feel instantly: when they ask an AI for “tons of ideas,” they may receive lots of phrases that look different on the surface but share the same underlying template. In other words, the output can increase apparent volume while reducing meaningful variation. This is how originality gets flattened - not by lack of quantity, but by repetition of the same structural idea under different wording.

The scientific grounding here is simple and mechanical: language models are good at producing plausible continuations. Plausibility is not the same as originality. When a prompt doesn’t provide constraints, the model leans on what it expects a “reasonable answer” to sound like. That tends to reproduce what already looks familiar. When a prompt provides a ladder - categories that shift, perspectives that rotate, and constraints that tighten - the model has to work harder to remain relevant while still generating different angles.

This is also where momentum comes from. Momentum is what happens when your next thought is easy to reach from the last one. Traditional brainstorming relies on the group’s energy and the facilitator’s ability to keep ideas flowing. Prompt-driven AI can create momentum by continuously offering “next rungs” of ideation - without the social friction of waiting for someone else to speak, and without the cognitive fatigue of starting from zero.

One counterintuitive detail is that AI can help originality most when you don’t ask it to be creative in the abstract. Instead, you ask it to explore systematically - variations, reframings, and constraint-driven twists. Creativity, in practice, often emerges from disciplined divergence, not from a single burst of inspiration. The ladder structure nudges divergence into forms that are easier to evaluate later, which means you spend less time staring at noise and more time selecting from signal.

A useful comparison is how photographers work. If you shoot only one composition repeatedly, you get consistent results but you might miss the shot that tells the real story. If you swing the camera wildly without a plan, you might get dramatic images but not a coherent set. Great photographers don’t just “take more pictures.” They shoot with deliberate variation. Prompting can be treated the same way: variation with a plan.

Nia at the Startup Desk: How the Ladder Shows Up in Real Product Design

Nia, 34, is a product designer at a startup where the team lives on fast cycles and tight decisions. Her work isn’t a grand design manifesto; it’s a sequence of trade-offs: what to build first, what to simplify, what to measure, what to leave alone. In that environment, brainstorming can’t be a separate ritual that produces ideas no one touches. It has to feed into decisions quickly enough that the product doesn’t drift away from reality.

The team’s typical brainstorming problem wasn’t a lack of energy. It was the sameness that crept in. After a few rounds, the ideas started to sound like variations of the same concept: new wording for the same flow, different visuals for the same interaction, a new feature that still assumed the same user behavior. Nia noticed that her own “internal evaluator” showed up early. The moment she saw an idea that didn’t feel right, she unconsciously started rejecting it, which reduced the number of directions worth exploring.

When she used the Spark Ladder Prompt Method, the difference wasn’t dramatic in the way people expect technology to be dramatic. It was gradual and structural. Rather than asking for an endless list, she used prompts that pushed the AI to generate ideas in shifting frames - each rung changing the angle while keeping the design anchored to the same product goal. The result was a spread of concepts that felt more like different paths through the same landscape, not a pile of random stones.

At her desk, she could feel momentum returning when the ladder gave her a clear “next” mental move. For example, when the prompts were sequenced to broaden idea variety and then tighten toward the product’s real constraints, she ended up with fewer dead ends. Not because the AI produced perfect answers, but because she spent less time converting raw output into shape. The ladder did that shaping for her by organizing the space of possibilities in a way her brain could scan.

There’s also a cultural angle here. In many teams, brainstorming is a social process. People hesitate to say certain thoughts because they might sound naive. AI changes that dynamic: it can surface options without requiring a person to “own” them immediately in the room. Nia still had to choose what mattered, but the AI lowered the barrier between “I have a rough thought” and “I can see how that thought might look in a product concept.” That matters in startups, where the cost of losing momentum is often paid in missed learning and delayed iteration.

And because Nia is working inside a living product, she isn’t just chasing novelty. The ladder’s narrowing stage forces ideas to connect to constraints that are hard to ignore: user needs, technical feasibility, and the fact that the team has limited time. That’s how idea volume becomes usable. The AI expands the number of candidate directions, and the ladder structure helps those candidates remain tethered to the decision space.

In practice, this is the difference between “more ideas” and “more design.” One creates options. The other creates options that can be turned into learning.

The Counterintuitive Part: Why Expanding Volume Can Preserve Originality

Here’s the surprise: the fastest way to protect originality during AI-assisted brainstorming is often to increase the number of ideas - then reduce the evaluation delay. When people hear “AI ideas,” they assume the risk is that the machine will replace taste. But the real risk is different: the evaluation timing. If you let the output wash over you without a structure to connect it to your problem, you can end up with a kind of creative numbness. Everything looks plausible; nothing feels necessary.

The Spark Ladder Prompt Method changes the timing by organizing the flow of ideation. It encourages divergence early - so you break out of looping categories - and then tightens attention so ideas start competing on criteria that reflect the real design challenge. That’s what preserves originality: not by blocking the AI’s influence, but by keeping human judgment engaged at the right moments.

This reframing matters because it changes how we think about “originality” in a world of generative tools. Originality isn’t only about having a unique idea. It’s also about choosing the idea that fits the problem, then pushing it forward in a way that reveals something true about the user and the context. A prompt ladder helps because it keeps the search wide enough to find genuine candidates, while keeping taste and constraints close enough to prevent the team from drifting into generic patterns.

The counterintuitive part is that “more” doesn’t necessarily dilute thinking. With the right structure, more can actually increase the chances that a distinctive idea survives the process.

What This Tells Us About Design, Taste, and the Social Life of Ideas

Design thinking often treats creativity like a private talent: something inside the head, waiting to be unlocked. Prompt-driven AI nudges that view. It shows that ideation is also a social and procedural system - shaped by rules about when to judge, how to categorize, and what counts as a relevant angle. Even Nia’s experience at her startup desk points to something larger: momentum isn’t just a feeling. It’s an outcome of structure.

There’s also a bigger lesson about tools and taste. AI can generate language that sounds like taste, but taste is more than what sounds good. Taste is what survives contact with constraints and learning. When prompts expand the space of possibilities without forcing the AI to “decide” for the designer, the human role becomes clearer: selecting, shaping, and refining. The machine widens the search; the designer keeps the thread.

So the mystery at the heart of this chapter isn’t whether AI can produce ideas. It’s what kind of thinking system we build around that production. If brainstorming is a choreography, prompts are the music - guiding where the dancers can go, and where they’re likely to stop. And that raises an unsettling, fascinating question: what does it mean for creativity when the next rung of your ladder is suggested instantly by a model that has never seen your product, your users, or your constraints?

End of chapter one. 4 more chapters in the full book.