Design

Framing problems and validating assumptions with LLMs

Use LLMs (primarily Claude and ChatGPT) to structure project framing: analyze context documents, define scope, map user flows, and challenge assumptions to build a clearer decision framework faster.

Why the human is still essential here

The designer remains responsible for the final framing, tradeoffs, and prioritization; AI provides structured analysis and alternative perspectives to evaluate.

How people use this

Assumption and risk register draft

Paste briefs and prior decisions and have an LLM generate explicit assumptions, unknowns, risks, and validation steps to pressure-test the plan.

Claude

Problem statement and success metrics rewrite

Iterate on a problem statement by asking AI to propose tighter scopes and measurable success metrics aligned to the business goal.

ChatGPT

User flow and edge-case mapping

Describe the current journey and ask AI to produce a step-by-step user flow with edge cases and dependencies to review with PM/Eng.

Miro AI

Community stories (1)

Medium

7 min read

How I Use AI to Scale Design Impact

AI didn’t change what I design. It changed how I design.

Over the past several months, my design process hasn’t just evolved — it’s been fully restructured. My AI tool stack isn’t something I use occasionally; it is an operational layer embedded into my day-to-day and across discovery, ideation, prototyping, validation, and delivery.

This article outlines how I structure projects using AI models — primarily Claude and ChatGPT — alongside specialized tools such as Figma Make and Amplitude.

Yuliia GalytskaProduct designer

Feb 27, 2026