The design process is dead. Here's what's replacing it. | Jenny Wen
How Anthropic's own design team works when the material being designed is a model.
Open lennysnewsletter.com →
Building & Product
Podcast
Podcast
Guide
Guide
Article
Article
Article
Article
Article
Article
Article
Article
Guide
Article
Guide
Article
Course
Article
How do I design AI features people trust (chat vs buttons, streaming, showing the work)?
A chat box is rarely the right interface: embedded AI (suggestions inside the existing workflow, one click to accept or reject) builds trust faster because users can see the AI's scope and undo its work. Stream responses so something appears within a second, show sources and reasoning where accuracy matters, and use fixed buttons with confirmation for anything risky. Design for the failure case first; how your product behaves when the AI is wrong is what users remember.
Go deeper
18 resources.
How Notion's design team uses Claude Code to prototype
Designing AI features by prototyping against real models, not static mocks.
Open lennysnewsletter.com →People + AI Guidebook
23 battle-tested design patterns for human-AI products, used by a quarter million builders.
Open pair.withgoogle.com →The Shape of AI: UX Patterns for Artificial Intelligence Design
A living pattern library (templates, modes, references, workflows) with real product examples.
Open shapeof.ai →Agent Management Interface Patterns
How users start, steer, and stop AI that works on their behalf, from a design veteran.
Open lukew.com →Showing the Work of Agents in UI
When to reveal the AI's reasoning and when it just adds noise.
Open lukew.com →First-Session Trust in AI Products: Why Code Editors Onboard Better Than Chatbots
Evidence-based case for embedded AI over chat, including GitHub Copilot's 96% same-day adoption.
Open uxmatters.com →Designing AI Chatbots: UX Principles for User Trust
Concrete trust numbers: confidence signals lift reliance 63%, consistency another 47%.
Open parallelhq.com →AI-First Product UX Patterns and Dark Patterns
Names the anti-patterns (fake confidence, hidden AI, forced chat) so you avoid shipping them.
Open buildmvpfast.com →AI Chat UI Best Practices
If you do build chat, this covers the table-stakes details users now expect.
Open thefrontkit.com →Chatbot UI UX Design Best Practices and Examples
A leading Indian design studio's practical chatbot patterns with examples.
Open lollypop.design →AI Chatbot UI Design: 8 Patterns That Build User Trust
Includes citation UI patterns, the single most effective trust device for factual products.
Open designpixil.com →AI Loading States Pattern
Exactly what to show in the 200ms-to-seconds gap before the first token arrives.
Open uxpatterns.dev →Loading UI/UX Patterns for AI Applications
Component-level guidance on skeletons, streaming text, and progress for AI waits.
Open telerik.com →Generative AI loading states (Cloudscape Design System)
Amazon's open design system spec for gen-AI states; steal it wholesale.
Open cloudscape.design →Streaming Responses: How to Build Snappy, Real-Time LLM UX
The engineering side of streaming UX: tokens on screen change perceived speed and trust.
Open medium.com →Building Trusted AI Products with the PAIR Guidebook (codelab)
A hands-on exercise applying the PAIR patterns to a product like yours.
Open codelabs.developers.google.com →UX Design Patterns for Loading and Feedback
The psychology of waiting, which AI products live or die by.
Open pencilandpaper.io →More in AI in Your Product
- Should my startup add AI features, and which ones actually matter to users? 20 →
- How do founders ship their first AI feature (APIs, wrappers, RAG in plain terms)? 19 →
- How much does it cost to run AI features, and how do I keep costs sane? 19 →
- Which AI model should I build on (GPT, Claude, Gemini, open-source), and how do I avoid locking myself in? 17 →
- How do I test whether my AI feature actually works before launch (evals, in plain terms)? 18 →
- How do I stop my AI feature from making things up in front of customers? 17 →
- Prompt engineering, RAG, or fine-tuning: which one does my product actually need? 18 →
- What is my moat if I'm building on someone else's model? 19 →
- Should I put an AI agent in my product, or is a simple workflow enough? 18 →
- Is it safe to send customer data to AI APIs, and what about privacy laws like India's DPDP Act? 18 →
- How should I price AI features: per seat, per use, or per outcome? 17 →
- My AI feature is live. How do I monitor it and make it better with real usage? 18 →
Also in Starting Up
The same ground, over in Build the product, our Starting Up track.
eChai Partner Brands
