Case study in progress

Leading with value on Grammarly's blank state

Timeline

Summer 2026

Mentored by

Hiếu Trần, TJ Eby

Overview

I redesigned Grammarly Editor’s blank state to help people get started and see value right away. I added clearer entry points to AI Chat and Proofreader, then built a blank-state system for every Grammarly agent ahead of the Superhuman Docs and Grammarly Editor merge.

Context

Grammarly Editor has a blank page problem.

Many people come to Grammarly as a final stop: they paste in finished text, then use Proofreader or the AI Detector for a final review. But people who open the Editor without text get little guidance or immediate value, so there’s no clear reason to start or come back.

Comparison of Grammarly Editor with writing present and on a blank page — Proofreader is useful once there’s text on the page. On a blank page, there’s no clear value or place to start.

The given brief

“Design these four quick starts to help users get text on the page.”

I was given four quick starts and their copy, and asked to figure out how they should appear on the blank canvas. I explored different placements and visual treatments, but the same problem remained: without context, why would someone choose one?

Early placement explorations for quick-start actions — I explored placements for the four quick starts within the main canvas, without using the side panel.

Exploration of Grammarly blank-state quick-start chips — But I kept coming back to the chips themselves:
Would anyone actually click one, and would the result feel useful?

Additional quick-start chip concepts and annotations — But I kept coming back to the chips themselves:
Would anyone actually click one, and would the result feel useful?

Reframing my own brief

Quick starts should feel obvious, low-effort, and clearly helpful to someone who isn’t sure where to begin.

Use-case-led AI entry point in Grammarly Editor — 1. Showing what AI Chat can do
“Help me write” only led to another blank surface. I replaced it with two specific starter prompts that opened AI Chat with an example already in motion, so people could see its value right away.

Demo text starter actions with clearer value propositions — 2. Giving Demo text a clearer purpose
Demo text can show Proofreader in action, but “Demo text” alone isn’t a very motivating CTA. I moved it into the empty Proofreader panel and framed it as a quick way to see Grammarly’s suggestions on a ready-made example.

Shipped experiment

Testing the new blank state with 500K+ Grammarly Editor users

Shipped Grammarly Editor experiment comparing control and test blank states — We compared the existing blank state with the new design in a 21-day experiment. The test was still running when my internship ended, so I don’t have final results to share.

Planning ahead

Designing a blank-state pattern that could scale beyond one agent or product.

The experiment had to work around other active tests and a tight engineering timeline. So I also looked beyond the immediate launch and designed a blank-state system that could support the Grammarly Editor and Superhuman Docs merge and scale across agents.

Leading with value on Grammarly's blank state

Grammarly Editor has a blank page problem.

Proofreader is useful once there’s text on the page. On a blank page, there’s no clear value or place to start.

“Design these four quick starts to help users get text on the page.”

I explored placements for the four quick starts within the main canvas, without using the side panel.

But I kept coming back to the chips themselves:
Would anyone actually click one, and would the result feel useful?

Quick starts should feel obvious, low-effort, and clearly helpful to someone who isn’t sure where to begin.

1. Showing what AI Chat can do

2. Giving Demo text a clearer purpose