How To Design In The Agent Era

Name: How To Design In The Agent Era
Uploaded: 2026-08-07T14:00:34.000Z
Duration: 56 min 1 s
Channel: Y Combinator

Y CombinatorAugust 7, 202656m

Topics60

Human Element in AI-Assisted Design0:00 Introduction to Paper0:37 Founder Background and Motivation2:00 AI-Native and Agent-Native Design Tool Definition3:00 Creative Workflow and Software Quality4:00 Paper Shaders and Visual Effects5:00 Real-World Shader Applications7:30 Image Generation and Brand Design Tools8:30 Marketing Through Product Development10:00 Design-to-Development Handoff11:30 Desktop App and Agent Integration12:30 Agent Workflow Demonstration13:30 Codebase Integration14:30 Source of Truth and Synchronization15:30 Chrome Extension and Live Site Integration16:30 Site Review: Legion Health17:00 Agent-Assisted Design Iteration19:00 Agent-Based Design Iteration Workflows20:32 The New Curation Process21:31 Agent Self-Correction Capabilities22:00 Model Selection Strategy22:30 Cursor as Agent Harness23:30 Branching Design Exploration24:00 Avoiding AI Design Tells24:31 Typography Refinement Rules25:00 Design Tool Integration Benefits26:00 Exporting Designs to Codebases26:30 Single-Person Design-to-Ship Workflows27:30 Agentic Workflow Requirements28:00 Sciteex Design Analysis28:30 Design Cleanup Process30:00 Model Instruction Guardrails31:30 Side-by-Side Comparison Value32:30 Business Impact of Design Quality33:00 Common AI Design Patterns34:00 Design Through Deletion35:00 Dark Mode Implementation Issues36:00 The Four Horsemen of AI Design36:30 Design Evolution and Competitive Positioning37:30 Moretta Design Review37:45 Value Proposition Clarity38:30 Balancing Energy and Trust39:00 Model Limitations and Human Control40:30 Agent Speed and Human Direction41:00 The Human Element in Agent-Assisted Design41:02 Can Agents Learn Design Taste41:30 The Challenge of Quantifying Design Judgment42:31 Models Will Improve at Tactics, Not Strategy43:00 How Paper Uses Agents Internally44:01 Small Elite Team Philosophy44:30 Designer-Led Website Creation with Agents45:00 Selective Agent Use46:00 Building a Values-Aligned Community47:02 Market Clock and Moving Up-Market48:00 Contrast with Previous Company49:31 Lessons Applied at Paper51:01 Bottleneck Philosophy51:31 Building an Informed Employee Base53:01 What Design Function Stays the Same53:30 What's Next for Paper55:00

In a Nutshell

Paper is an AI-native design tool that uses HTML/CSS as its rendering engine to enable seamless agent integration, allowing designers to work at agent speed while maintaining human oversight for taste and strategy. The key advantage is treating codebases as the single source of truth—agents can directly manipulate designs without translation overhead, enabling one person to handle work previously requiring entire teams. The critical takeaway is that agents excel at tactical execution and iteration but cannot replace human judgment in strategic design decisions like value proposition clarity, brand positioning, and what differentiates companies.

AI-Generated Notes

These notes were generated by AI and may contain inaccuracies.

Agents can speed up workflows and handle tasks like translation or resizing, but the human element of design remains essential. The goal is creating tools that enable humans to work faster with agents rather than replacing human creativity. Using whatever cloud design generates does not help companies stand out, as exceptional design differentiates great companies from the crowd. Every successful company from the last 10-20 years has had exceptional design, making investment in design essential for building a great company.

Steven Haney founded Paper, an AI-native design tool experiencing rapid adoption. Y Combinator uses Paper extensively for all internal design work. Paper is a design tool that uses HTML and CSS as the actual rendering engine, making it agent-native since agents understand HTML and CSS well. Traditional design tools with custom rendering engines create higher token spend, slower performance, and lower accuracy for agents.

Paper is a team of 12 designers and engineers who started from a love of design and are building the best design tool for the agent era. Many founders building AI-native companies specifically seek AI-native tools from the ground floor.

Paper originated from a love of design as a solo founder side project. Haney believes founders should pursue projects they would do anyway, emphasizing founder-market fit. Building tools for creative professionals is something Haney would wake up excited about daily, representing strong founder-market fit.

Existing tools like Figma have contributed significantly to the design industry and serve enterprise companies well, but there's opportunity for a new tool focused on designers that addresses AI and agent changes. The approach builds on HTML and CSS to create a next-generation, agent-native tool.

Being agent-native centers on fundamental technology choices. Using HTML and CSS as the rendering engine was initially intended to improve designer-developer handoff by creating constraint-free systems that feel like Figma or Sketch while being HTML underneath. This approach benefits agents because they understand HTML and CSS from their training data. When agents work with Paper files, they read CSS directly without translation issues.

Paper functions as both a design tool and a visual interface for agents. Sales professionals, engineers, and others use it because prompting isn't always optimal for agents - sometimes direct manipulation through drag and draw is faster.

Sign in to read the full notes

Get access to AI-generated notes, topic timestamps, and more.

How To Design In The Agent Era

Human Element in AI-Assisted Design00:00

Introduction to Paper00:37

Founder Background and Motivation02:00

Sign in to read the full notes