scripod.com
Gamma’s head of design shares how his small team uses AI to synthesize feedback, generate on-brand imagery, and maintain design quality while serving users in 60+ countries | Zach Leach

Overview

Shownote

Highlights

Transcript

Chapters

Pins

Gamma’s head of design shares how his small team uses AI to synthesize feedback, generate on-brand imagery, and maintain design quality while serving users in 60+ countries | Zach Leach

How I AI

2025/06/09
How I AI

How I AI

2025/06/09
OverviewShownoteHighlightsTranscriptChaptersPins

Shownote

Zach Leach, head of design at Gamma, reveals how his small team uses AI to analyze global feedback, create on-brand imagery, and maintain design quality while serving users in more than 60 countries. What you’ll learn: 1. How Gamma analyzes feedback fr...

Highlights

In this episode, Zach Leach from Gamma discusses how his team leverages AI to manage and analyze global feedback, create consistent brand imagery, and streamline design processes. The focus is on using advanced tools like ChatGPT, Midjourney, and Replicate to improve workflows and maintain quality across a diverse user base.
02:43
Gamma's user base is 60% international with notable global revenue.
05:25
A significant portion of feedback is in non-English languages.
09:11
ChatGPT processes 550 responses in a week, far exceeding manual capabilities.
10:11
Deep research offers better quality insights than basic scripts.
12:40
AI classified diverse user feedback and generated a presentation in 20 minutes.
19:53
Prompt evolution in Midjourney is key to generating effective images.
23:54
Replicate is a fast and high-quality tool for background removal.
25:41
Use Midjourney with style references for on-brand images
31:51
Drizzling caramel on something saves time.
32:28
Making things fun is crucial for human designers amidst AI advancements.

Chapters

Intro
00:00
Building the Gamma AI image editing feature
02:42
Using ChatGPT’s deep research for feedback analysis
05:25
How feedback was analyzed before AI tools
09:10
Benefits of deep research vs. basic scripting
10:10
Insights from ChatGPT's deep research
12:40
Demo of Midjourney workflow for creating on-brand art
16:41
Using Replicate for background removal
23:54
Style references (SREF) and brand consistency in Midjourney
25:40
An AI workflow for creating consistent job descriptions
29:19
Conclusion and final thoughts
32:27

Transcript

Claire Vo: About how many pieces of feedback did you analyze this? Is this dozens? Is this hundreds? Zach Leach: Over the course of a week, we got about 550 individual responses. What I thought would actually work really well is something like ChatGPT's d...