Visual Design Principles for User Experience

The best UX lessons hide in unexpected places. Take birth control pill packets. Most people see pharmaceutical packaging. I see a masterclass in contextual design. Three things this simple product gets right: 1. No fixed starting point. Thanks to the loop, you can start on any day, and the system will adapt to you, not the other way around. 2. No additional tracking needed. Empty bubble = taken. Full bubble = not taken. Zero cognitive load added to your life. 3. Just-in-time information. You see exactly what you need, when you need it. The information lives where exactly the pills are taken Here's how you can apply this in digital products: The best interfaces don't make users remember things. They show the state at the moment users need to make a decision. Most apps over-rely on notifications and external reminders. This packet design proves you can embed the tracking directly into the interaction itself. So serve information exactly when and where it's needed, with minimal setup. What's a physical product that taught you about great design?

𝗗𝗲𝘀𝗶𝗴𝗻𝗶𝗻𝗴 𝗖𝗼𝗻𝘁𝗲𝘅𝘁-𝗔𝘄𝗮𝗿𝗲 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀: 𝗧𝗵𝗲 𝟲 𝗗𝗶𝗺𝗲𝗻𝘀𝗶𝗼𝗻𝘀 𝗼𝗳 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 Building AI agents isn’t just about fine-tuning prompts or plugging in APIs. The real differentiator lies in how effectively we design and manage context. Context defines the agent’s role, behavior, reasoning, and decision-making. Without it, even the best models act inconsistently. With it, agents become reliable, explainable, and enterprise-ready. Here are the 6 essential types of context for AI agents:  1. 𝗜𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻𝘀 – Define the who, why, and how: • Role (persona, e.g., PM, coding assistant, researcher) • Objective (business value, outcomes, success criteria) • Requirements (steps, constraints, formats, conventions)  𝟮.𝗘𝘅𝗮𝗺𝗽𝗹𝗲𝘀 – Demonstrate desired (and undesired) patterns: • Behavior examples (step sequences, workflows) • Response examples (positive/negative outputs)  𝟯.𝗞𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 – Embed domain and system understanding: • External context (business model, strategy, systems) • Task context (workflows, procedures, structured data)  𝟰.𝗠𝗲𝗺𝗼𝗿𝘆 – Extend reasoning across time: • Short-term memory (chat history, state, reasoning steps) • Long-term memory (facts, episodic experiences, procedural instructions) 𝟱.𝗧𝗼𝗼𝗹𝘀 – Extend capability beyond training data: • Tool descriptions act as micro-prompts • Parameters and examples guide usage 𝟲.𝗧𝗼𝗼𝗹 𝗥𝗲𝘀𝘂𝗹𝘁𝘀 – Close the loop by feeding outputs back into reasoning: • Orchestration layers attach results • Enables agents to adapt dynamically 𝗪𝗵𝘆 𝗶𝘁 𝗺𝗮𝘁𝘁𝗲𝗿𝘀: By designing across all six dimensions, we move beyond “prompt engineering” into structured context engineering. This makes agents: • More autonomous • More explainable • Easier to scale across enterprise systems In practice, this framework underpins everything from agent orchestration protocols (MCP, A2A) to multi-agent architectures in production. Question for you: When building AI agents, which of these six contexts have you found most challenging to implement at scale?

Wow. I just built 3 mini-apps for PMs in under 10 minutes: an empathy mapper, a journey analyzer, and a competitive analysis tool with Opal (Google Labs). No PRD. No Figma. No tickets. Just an idea → an experience. Instead of debating documents, I’m now sharing working mini-apps with my team ask them "react to this, let’s refine it” I used Opal to prototype the vibe with an: -Empathy Mapper -User Journey Analyzer -Competitive Landscape Tool Each one took minutes. Each one was immediately shareable. Each one changed the conversation. Use Opal when: -You want to validate an idea before writing a PRD -You need a quick tool for a workshop or meeting -You want to make research or concepts visible -You want to better empathize about your user Think of Opal as your 10-minute lab. If it takes longer than that, move it to a full prototype — that’s where other AI prototyping tools come in. Tips for PMs adopting this workflow -Start tiny. Your first Opal app should take under ten minutes. That constraint keeps you focused on intent, not polish. -Think in verbs, not nouns. Prompts like “summarize feedback” or “visualize trends” produce far better prototypes than static descriptions. -Collaborate live. Invite designers, engineers, and stakeholders into the session. Watching the prototype evolve creates alignment faster than any meeting. -Reflect. After every prototype, note what worked. Each build sharpens your prompting instincts and your product intuition. 🔗 Guides + masterclass in the comments 👇

PROTOTYPES ACCELERATE DISCOVERY, NOT DELIVERY Prototypes are powerful tools for the discovery phase — helping teams quickly explore product directions, validate concepts with customers through high-fidelity experiences, and align executives around tangible visions. The leverage they provide in answering "what's the right experience to build?" is remarkable. However, I frequently see PMs expecting to hand prototypes directly to engineering teams for production implementation. This approach consistently leads to disappointment. Here's why: prototype code isn't built to meet the security, reliability, robustness, and maintainability standards that production systems require. Your engineering team rightfully prioritizes these critical attributes. And that's perfectly fine. The value of prototypes lies entirely in discovery. Even when engineering teams ultimately rebuild from scratch, prototypes have already delivered tremendous ROI by: - Accelerating team alignment on product direction - Validating customer demand with realistic experiences - Securing executive buy-in through tangible demonstrations The code was never meant to ship — the insights were.

Anthropic just introduced Contextual Retrieval, and it's a significant yet logical step up from simple Retrieval-Augmented Generation (RAG)! Here are the steps to implement Contextual Retrieval based on Anthropic's approach: 1. Preprocess the knowledge base: - Break down documents into smaller chunks (typically a few hundred tokens each). - Generate contextual information for each chunk using Claude 3 Haiku with a specific prompt. - Prepend the generated context (usually 50-100 tokens) to each chunk. 2. Create embeddings and a BM25 index: - Use an embedding model (Gemini or Voyage recommended) to convert contextualized chunks into vector embeddings. - Create a BM25 index using the contextualized chunks. 3. Set up the retrieval process: - Implement a system to search both the vector embeddings and the BM25 index. - Use rank fusion techniques to combine and deduplicate results from both searches. 4. Implement reranking (optional but recommended): - Retrieve the top 150 potentially relevant chunks initially. - Use a reranking model (e.g., Cohere reranker) to score these chunks based on relevance to the query. - Select the top 20 chunks after reranking. 5. Integrate with the generative model: - Add the top 20 chunks (or top K, based on your specific needs) to the prompt sent to the generative model. 6. Optimize for your use case: - Experiment with chunk sizes, boundary selection, and overlap. - Consider creating custom contextualizer prompts for your specific domain. - Test different numbers of retrieved chunks (5, 10, 20) to find the optimal balance. 7. Leverage prompt caching: - Use Claude's prompt caching feature to reduce costs when generating contextualized chunks. - Cache the reference document once and reference it for each chunk, rather than passing it repeatedly. 8. Evaluate and iterate: - Run evaluations to measure performance improvements. - Adjust parameters and techniques based on your specific use case and results.

UI Principles Mini-Series, 2 of 5: The Law of Similarity Why do some interfaces feel instantly organised? Because our brains group things that look alike. When elements are visually similar, we perceive them as related. Use similarity on purpose:

 🔹Colour is the strongest cue. Reserve your highlight colour for interactive elements like links and buttons, not for decorative headlines.
 🔹Size signals hierarchy and relatedness. Keep comparable items the same size, and differentiate intentionally.
 🔹Shape creates family ties. A consistent button shape reads as one group and sets the expectation of clickability.
 🔹You can combine cues. Orientation, behaviour, and movement also reinforce grouping. Aligned items, shared hover states, or matching micro-interactions feel like one set. Build it into your system:
 Create a clear style guide. Define a colour palette with neutrals, highlight, and action colours. Set type styles for headings, body, links, buttons etc. Apply the same tokens and rules inside components so users get consistent signals.

 Watch out for traps:
 If everything looks clickable, nothing is clear. Do not rely on colour alone for meaning. Pair colour with size, shape, labels, or underlines. Check contrast and test with real users so visual polish does not mask usability issues. 💡 Takeaways
 • Visually similar items are perceived as related
 • Start with a system: colour roles, type scales, and component rules
 • Use similarity to guide, not to decorate
 • Pair colour with size and shape for clarity and accessibility
 • Validate with testing so appearance does not overrule reality
 In short: make related things look related, and make interactive things look interactive.
 Next up in the series: another favourite principle to sharpen your design eye. Make sure to follow. 📚 → Full UI Principles course: https://lnkd.in/dyAHJdU3
 📚 → All my courses: moonlearning.io/store
 ✉️ → Newsletter (free): moonlearning.io/newsletter

What if the best solutions for your process started with cardboard? When testing new ideas or improvements, jumping straight to high-cost, permanent solutions can be risky—and expensive. That’s where cardboard engineering comes in. Cardboard is one of the simplest, most cost-effective tools for rapid prototyping and testing ideas. It’s lightweight, easy to shape, and lets you visualize, test, and refine your concepts before committing to more expensive materials. Why Cardboard Is Perfect for Prototyping: 1️⃣ Low-Cost Experimentation Testing with cardboard lets you try multiple iterations of a design without worrying about material costs. 2️⃣ Fast Feedback Loops You can build and modify a prototype in minutes, gathering instant feedback from your team or operators. 3️⃣ Hands-On Collaboration Cardboard prototypes allow teams to actively engage with ideas, making it easier to identify issues or opportunities for improvement. 4️⃣ Visual Validation Sometimes, seeing a physical model highlights challenges that wouldn’t be obvious in a drawing or plan. How to Use Cardboard for Lean Improvements: 🔍 Test Workstation Layouts Use cardboard cutouts to mock up layouts and placement of tools, parts, and equipment. Adjust until everything flows smoothly. 📦 Simulate Material Flow Prototype racks, bins, or carts to ensure materials are stored and moved efficiently before building them with more durable materials. 🛠️ Design Fixtures or Jigs Create cardboard versions of fixtures or jigs to test their functionality in the process. Refine the design before investing in the final version. 📐 Test Ergonomics Mock up equipment or workstation designs with cardboard to test ease of use, reach, and operator comfort. Example of Cardboard in Action: A manufacturing team wanted to redesign a workstation to reduce operator motion. Instead of committing to expensive reconfigurations, they used cardboard to prototype the layout. After several iterations, they found the optimal setup, reducing motion by 25% and saving hours of work. Cardboard isn’t just for packaging—it’s a powerful tool for testing and refining your ideas. By prototyping with low-cost materials, you can experiment, learn, and improve quickly without breaking the bank.

This is Colour One of the things I love about Richard Rogers’s buildings (and his shirts) was his ability to embrace colour. Colour is a powerful tool in architecture and design, but there is nowhere to hide — and as a result it can be one of the scariest too. Grey and beige are often ‘safe bets’, but when used with skill, colour can be a beautiful antidote to a dull built environment. At its simplest, colour can be described in terms of hue (the colour itself), saturation (a colour’s intensity), and lightness (how light or dark it appears). Isaac Newton demonstrated that white light contains the full visible spectrum — long observed in the rainbow — and arranged these colours in a wheel to reveal their relationships. This work became the foundation of modern colour theory and, ultimately, the development of the standardised colour systems we use today. There are some core principles that all designers need to understand when working with and specifying colour: – Additive colour Applies to light and screens (not printed or painted colour). Colour is created by combining red, green and blue light (RGB). – Subtractive colour Applies to pigments and print. Unlike light, adding more pigment absorbs more light, so colours become darker and less vivid. The primary pigments are cyan, magenta and yellow, with black added for control (CMYK). – Perceptual systems Colour wheels and colour harmonies are used to organise and balance schemes. As there are countless possible combinations, colour systems have been developed to allow consistent and repeatable specification — such as RAL and Pantone. It is also important to recognise that colour is experienced differently across cultures, and from person to person. This graphic brings together some of the key fundamentals of colour theory used in design practice. This post is intended only as an introduction. Always refer to authoritative sources, colour standards and manufacturer data when developing or specifying colour schemes. Further reading 📚 Newton — Opticks 📚 Josef Albers — Interaction of Color 📚 RAL & Pantone colour systems — standardised colour specification 📚 BS / ISO colour and appearance standards If you’re studying architecture, working in construction, or enjoy understanding how buildings are put together, consider following for regular “this is a…” posts. #architecture #design #colourtheory #architecturaleducation #buildingmaterials #interiordesign #thisisa #visualcommunication

How Itten’s color theory can teach us to design more accessible interfaces Lately I read about Johannes Itten’s color theory from the Bauhaus, and I was surprised by how relevant it feels for modern accessibility. We usually design according to WCAG contrast ratios, which are essential for readability, especially for people with low vision, age-related sight loss, or color-vision deficiencies. But contrast is not only a number, it is an important human experience. ✨ Research shows that perception is more complex than a simple ratio. A recent study on simultaneous color contrast found that surrounding colors can change how bright or saturated an element appears, even if its values stay the same. This means a “WCAG-passing” color combination can still feel unclear or uncomfortable for users sensitive to contrast or with visual processing differences (the link to the study: https://lnkd.in/eBynmhrr) Accessibility guidelines also note that poor contrast impacts many more people than we usually think: older adults, people using screens in bright light, or users with cognitive load who rely on clear visual hierarchy. Itten identified seven types of color contrast (light–dark, hue, saturation, warm–cool, complementary, simultaneous, and extension/proportion). While not all are part of WCAG, they offer a richer way to design for diverse perception: • Light–dark supports users with low vision - it's a foundation of WCAG. • Hue & saturation help people with color-vision deficiencies who rely on differences beyond classic red/green cues. • Simultaneous contrast reminds us that background colors can distort readability - important for users with migraines or sensory sensitivity. • Extension (proportion) helps create hierarchy for users who struggle with attention or cognitive overload. • Complementary contrast boosts differentiation when combined with sufficient luminance contrast. Here's a recent review of Itten’s work shows how his ideas still shape color education today: https://lnkd.in/eE7hVzmc So instead of treating contrast ratio as a pass/fail checkpoint, we can think in layers: ✔ Start with WCAG luminance contrast (the baseline for accessibility) ✔ Add Itten-inspired contrasts to strengthen perceptual clarity ✔ Test in different environments (low light, bright sun, low saturation modes) ✔ Consider users with diverse visual abilities (low vision, CVD, cognitive load, sensory sensitivity) It’s a reminder that accessible colour design is not only a mathematical problem, in reality it is a perceptual, human, systemic one. #Accessibility #WebAccessibility #A11y #InclusiveDesign #UXDesign #UIUX #UserExperience #ColorTheory #JohannesItten

Adobe Target vs Adobe Journey Optimizer (AJO): What’s the Real Difference? This question keeps surfacing — so let’s clear it up: Adobe Target is built for on-site personalization — A/B testing, recommendations, and experience targeting on websites and apps. Adobe Journey Optimizer (AJO) is designed for cross-channel journey orchestration — triggering emails, SMS, push notifications, and actions based on real-time events and unified profiles. Key distinction: Target optimizes a single moment (e.g., the web experience). AJO orchestrates the full customer lifecycle across channels. In advanced use cases, they work together — AJO runs the journey, Target personalizes the experience at each touchpoint. Use Case 1: Only Adobe Target Scenario: A retail brand wants to test homepage banners for different customer segments. What Target Does: Shows Banner A to new visitors, Banner B to returning customers. Runs A/B test to determine which banner drives more engagement. Why Target Alone? It’s purely on-site personalization, real-time, and doesn’t need journey orchestration. Use Case 2: Only Adobe Journey Optimizer (AJO) Scenario: A financial institution sends automated onboarding emails after account creation. What AJO Does: Triggers a welcome email journey once a new customer profile is created. Follows up with SMS reminders over 7 days if onboarding steps are not completed. Why AJO Alone? It’s a multi-step, cross-channel journey, driven by real-time events. Use Case 3: Target + AJO Together Scenario: A travel brand sends personalized trip offers via email, and follows up on the website. How They Work Together: AJO triggers an email based on recent travel searches. When the customer clicks the email and visits the site, Target personalizes the landing page to highlight related packages. Why Both? AJO handles orchestration of the journey. Target handles personalization at the point of web interaction. #AdobeExperienceCloud #AdobeJourneyOptimizer #AdobeTarget #CustomerJourney #DigitalPersonalization #MarTech #AEP