Intuitive Interaction Methods

Human conversation is interactive. As others speak you are thinking about what they are saying and identifying the best thread to continue the dialogue. Current LLMs wait for their interlocutor. Getting AI to think during interaction instead of only when prompted can generate more intuitive and engaging Humans + AI interaction and collaboration. Here are some of the key ideas in the paper "Interacting with Thoughtful AI" from a team at UCLA, including some interesting prototypes. 🧠 AI that continuously thinks enhances interaction. Unlike traditional AI, which waits for user input before responding, Thoughtful AI autonomously generates, refines, and shares its thought process during interactions. This enables real-time cognitive alignment, making AI feel more proactive and collaborative rather than just reactive. 🔄 Moving from turn-based to full-duplex AI. Traditional AI follows a rigid turn-taking model: users ask a question, AI responds, then it idles. Thoughtful AI introduces a full-duplex process where AI continuously thinks alongside the user, anticipating needs and evolving its responses dynamically. This shift allows AI to be more adaptive and context-aware. 🚀 AI can initiate actions, not just react. Instead of waiting for prompts, Thoughtful AI has an intrinsic drive to take initiative. It can anticipate user needs, generate ideas independently, and contribute proactively—similar to a human brainstorming partner. This makes AI more useful in tasks requiring ongoing creativity and planning. 🎨 A shared cognitive space between AI and users. Rather than isolated question-answer cycles, Thoughtful AI fosters a collaborative environment where AI and users iteratively build on each other’s ideas. This can manifest as interactive thought previews, real-time updates, or AI-generated annotations in digital workspaces. 💬 Example: Conversational AI with "inner thoughts." A prototype called Inner Thoughts lets AI internally generate and evaluate potential contributions before speaking. Instead of blindly responding, it decides when to engage based on conversational relevance, making AI interactions feel more natural and meaningful. 📝 Example: Interactive AI-generated thoughts. Another project, Interactive Thoughts, allows users to see and refine AI’s reasoning in real-time before a final response is given. This approach reduces miscommunication, enhances trust, and makes AI outputs more useful by aligning them with user intent earlier in the process. 🔮 A shift in human-AI collaboration. If AI continuously thinks and shares thoughts, it may reshape how humans approach problem-solving, creativity, and decision-making. Thoughtful AI could become a cognitive partner, rather than just an information provider, changing the way people work and interact with machines. More from the edge of Humans + AI collaboration and potential coming.

Intuitiveness is a "briefcase word" - it needs to be unpacked to be meaningful. And yet we often see "intuitive UI" used as a description of a feature, or worse, a product *requirement.* One issue is that "intuitive" really has two components, and you need both for a good product. One is the delta between the mental model of the product's designer and its user; it's "intuitive" if the workflow the user is accustomed to is mirrored precisely by the interface. The UI presents interactive elements in the hierarchy *and order* that the user looks for them, the affordances "speak the language" of that user. Designers trying to make "intuitive" interfaces often think they can achieve this by hiding complexity. But if their users are *looking* for that complexity, the design will be a disaster; the complex needs to be made *understandable* rather than merely simple. The other side of "intuitive" is the product's effectiveness at teaching its mental model to the user. This is necessary if - like any good innovation - you've come up with a new and better way of doing something. A really good primer on this is Arin Hanson's "Sequelitis" - exploring how the first few screens of Mega Man X introduce new mechanics that players of the other Mega Man games would be unfamiliar with. Another good example is Solitaire - training Windows users of bygone days to operate the newfangled thing called a "mouse" and practice interaction techniques like dragging and dropping. A product that only engaged with "intuitiveness" in the first way would be completely impenetrable to new users who weren't already experts in the old way of doing things. But a product that only engaged with it in the second way would be extremely frustrating for those expert users, who will initially make up your user base and don't want you to reinvent their wheel. Customizability is another element that often comes up - rather than make users re-learn, we let them adapt the system to their mental model - but it's usually used as a crutch by product teams who are not willing to learn that mental model in the first place. Customization created under this paradigm tends to be the opposite of intuitive, requiring lengthy 3rd party guides. This nuance is why designers must never rely on stakeholder approval as the "user acceptance test" of their work. What's "intuitive" for an exec is likely useless to a worker.

Intelligent interfaces make real-time design choices. For designers, sharing design decisions with robots can be… uncomfortable. But delegation ≠ abdication. The new work for designers is to give context and guidance to help the system make good choices. I made a guide, demo, and video for designers (link in the comments) about how to do this and keep the results on the rails. Done right, the result is a radically adaptive experience that responds to user context and intent. Layouts that rearrange themselves. Forms that choose smart defaults. Chat that “speaks” with well chosen GUI elements instead of text. It’s easier and more reliable than you might expect. The guide includes a simple, directional pattern library for giving the LLM its marching orders. For designers, sketching in simple plain-language system prompts becomes part of the design process, at least as important as drawing interfaces in your design tool. Instead of designing every interaction, you’re designing the *physics* of your application’s tiny universe. You define the behavior and constraints for making design decisions in the interface. It’s design system work for real-time decision-making. The basic recipe for wiring interface to intent: 1. Provide a constrained set of UI outputs. 2. Map those outputs to intent (“use this pattern to address that intent”). 3. Ask the LLM to understand intent and choose the right UI or action. It used to be really, really hard for systems to determine user intent from natural language or other cues. Now LLMs just get it. They grasp underlying semantics, they get slang, they can infer from context. LLMs may hallucinate facts, but they’re brilliant at interpreting intent and the shape of the expected response. This makes them a powerful and reliable partner for interpreting user meaning and delivering an appropriate interface. Check out the demo and give it a try yourself. Start writing; the interface is listening. Link in the comments (because you know, LinkedIn).

I brainstormed a list of things I ask myself about when designing for Human-AI interaction and GenAI experiences. What's on your list? • Does this person know they are interacting with AI? • Do they need to know? • What happens to the user’s data? • Is that obvious? • How would someone do this if a human was providing the service? • What parts of this experience are improved through human interaction? • What parts of this experience are improved through AI interaction? • What context does someone have going into this interaction? • What expectations? • Do they have a specific goal in mind? • If they do, how hard is it for them to convey that goal to the AI? • If they don't have a goal, what support do they need to get started? • How do I avoid the blank canvas effect? • How do I ensure that any hints I provide on the canvas are useful? • Relevant? • Do those mean the same thing in this context? • What is the role of the AI in this moment? • What is its tone and personality? • How do I think someone will receive that tone and personality? • What does the user expect to do next? • Can the AI proactively anticipate this? • What happens if the AI returns bad information? • How can we reduce the number of steps/actions the person must take? • How can we help the person trace their footprints through an interaction? • If the interaction starts to go down a weird path, how does the person reset? • How can someone understand where the AI's responses are coming from? • What if the user wants to have it reference other things instead? • Is AI necessary in this moment? • If not, why am I including it? • If yes, how will I be sure? • What business incentive or goal does this relate to? • What human need does this relate to? • Are we putting the human need before the business need? • What would this experience look like if AI wasn't in the mix? • What model are we using? • What biases might the model introduce? • How can the experience counteract that? • What additional data and training does the AI have access to? • How does that change for a new user? • How does that change for an established user? • How does that change by the user's location? Industry? Role? • What content modalities make sense here? • Should this be multi-modal? • Am I being ambitious enough against the model's capabilities? • Am I expecting too much of the users? • How can I make this more accessible? • How can I make this more transparent? • How can I make this simpler? • How can I make this easier? • How can I make this more obvious? • How can I make this more discoverable? • How can I make this more adaptive? • How can I make this more personalized? • How can I make this more transparent? • What if I'm wrong? ------------ ♻️ Repost if this is helpful 💬 Comment with your thoughts 💖 Follow if you find it useful Visit shapeofai.substack.com and subscribe! #artificialintelligence #ai #productdesign #aiux #uxdesign

Exploring new interaction design patterns for Contextual Prompt Manipulation Part-2⚡️ As we move deeper into AI-driven creative tools, I have been exploring how interface design can empower users to refine AI outputs faster without constantly rewriting prompts. While conversational AI has made intent-to-outcome flows faster, we’re still just scratching the surface in designing controls that help users manipulate prompts contextually and get to value quicker. Here are four emerging patterns I’ve been experimenting with: 𝟭. 𝗖𝗼𝗻𝘁𝗲𝘅𝘁𝘂𝗮𝗹 𝗮𝘀𝗽𝗲𝗰𝘁 𝗿𝗮𝘁𝗶𝗼 𝗰𝗼𝗻𝘁𝗿𝗼𝗹 Interactive sliders or toggles that let users fine-tune aspect ratios (e.g., 1:1 → 3:2 → 16:9) 𝟮. 𝗣𝗿𝗼𝗺𝗽𝘁 𝘁𝘂𝗻𝗶𝗻𝗴 𝗸𝗻𝗼𝗯𝘀 Circular, synth-like controls to adjust variables such as creativity, energy, tone, or complexity making it intuitive to “dial in” the right AI response. 𝟯. 𝗜𝗻𝗹𝗶𝗻𝗲 𝗱𝗿𝗼𝗽𝗱𝗼𝘄𝗻 𝗽𝗿𝗲𝘀𝗲𝘁𝘀 Quick-select dropdowns embedded directly in the input flow, enabling users to choose from pre-set styles, tones, or parameters without leaving the context. 𝟰. 𝟮𝗗 𝘁𝗼𝗻𝗲 𝗺𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗼𝗿𝘀 Dual-axis grids for blending multiple tonal attributes simultaneously — e.g., Casual ↔ Formal and Witty ↔ Persuasive in a single gesture. These controls shift the experience from prompt writing to prompt shaping, helping users co-create with AI more fluidly. Both first and fourth UI control ideas are inspired by Pablo Stanley on Lummi Would love to hear any more ideas on this. 👉 Where else have you seen contextual prompt manipulation done well? #GenerativeAI #productmanagement #ProductDesign #uiux #DesignThinking #ArtificialIntelligence

Ever noticed how push/pull doors still confuse people? When a door looks the same on both sides, users have to stop, read “PUSH” or “PULL,” and then act. That tiny pause may seem harmless - but in high-stress moments (like entering a hospital), even small friction matters. Good UX doesn’t ask users to think. It guides them instinctively. Instead of relying on text: - A handle naturally suggests pull - A flat plate clearly indicates push The form itself communicates the action. ✨ Less thinking ✨ Faster interaction ✨ Better accessibility ✨ More confident users When design is clear, behavior becomes effortless. That’s what good UX looks like. 📌 Save this post  👉 Follow Charmi Gangani for more design insights.  . .  . #UIUXDesigner #UIUXDesign #UIDesign #UXDesign #UserExperience #UserInterface #ProductDesign #DesignTips #UXTips #UITips #DesignThinking #DigitalDesign #WebDesign #MobileAppDesign #FigmaDesign #UIDesigner