
Gamma’s head of design on using AI to synthesize feedback and generate on-brand imagery | Zach Leach
Claire Vo (host), Zach Leach (guest)
In this episode of How I AI, featuring Claire Vo and Zach Leach, Gamma’s head of design on using AI to synthesize feedback and generate on-brand imagery | Zach Leach explores gamma design leader uses AI for feedback synthesis and branding Zach Leach (Head of Design at Gamma) shows how he uses AI as a research assistant to digest large volumes of messy, multilingual product feedback—about 550 responses in a week—without manually translating or sampling only a small subset.
Gamma design leader uses AI for feedback synthesis and branding
Zach Leach (Head of Design at Gamma) shows how he uses AI as a research assistant to digest large volumes of messy, multilingual product feedback—about 550 responses in a week—without manually translating or sampling only a small subset.
He demonstrates using ChatGPT “deep research” to translate, summarize, and classify feedback by themes (what’s working, what isn’t, prompt patterns), then exporting those classifications for charts and team-ready reporting.
On the brand side, he walks through a Midjourney-based workflow that uses style references/personalization to rapidly iterate toward consistent, art-directed imagery for UI “empty states,” plus Replicate models for fast background removal before dropping assets into Figma.
Finally, he shares a lightweight Claude “project” workflow to standardize job descriptions across hiring managers, and reflects on what human designers should keep owning: fun, personality, and craft details.
Key Takeaways
Deep research turns unstructured feedback into usable product signals.
Instead of hand-reviewing a tiny sample, Zach uploads a feedback file and lets ChatGPT deep research translate, summarize, and identify what’s working/not working, including prompt-level patterns across many languages.
Get the full analysis with uListen AI
Quality of analysis improves when moving beyond keyword scripts.
Zach contrasts deep research with a prior approach: Python keyword matching (or row-by-row prompting). ...
Get the full analysis with uListen AI
Feedback classification becomes a pipeline, not a one-off summary.
After deep research, he asks for per-row categorization and exports it into a spreadsheet to graph outcomes (e. ...
Get the full analysis with uListen AI
Model tier differences show up in measurable satisfaction gaps.
Gamma compared paid vs free user feedback because different model access can change outcomes; they observed ~5% rating difference, reinforcing that model choice materially affects UX.
Get the full analysis with uListen AI
User complaints can directly inform UX “guardrails” for prompting.
A key issue was multi-step edits failing (the model completes only part of a compound request). ...
Get the full analysis with uListen AI
Style references make AI image generation operational for brand teams.
Gamma codified an “airy, surreal, vivid” art direction into Midjourney style reference/personalization plus shared prompt conventions—turning brand consistency into a repeatable internal kit.
Get the full analysis with uListen AI
AI tooling frees time for craft—where differentiation still matters.
By automating research synthesis and asset generation (including background removal via Replicate), the team can invest in fit-and-finish details (e. ...
Get the full analysis with uListen AI
Notable Quotes
“Over the course of a week, we got about 550 individual responses.”
— Zach Leach
“If I’m being totally honest, I probably would’ve hand-looked at maybe 20.”
— Zach Leach
“It sort of went through all the feedback, understood what’s working, what’s not working, what prompts work, what don’t work.”
— Zach Leach
“It’s almost like I can follow those rabbit holes of creativity.”
— Zach Leach
“I would hope that it’s never gonna be as good as making things fun.”
— Zach Leach
Questions Answered in This Episode
What exact column structure and prompt did you give ChatGPT deep research to get reliable per-row classifications (and reduce hallucinated categories)?
Zach Leach (Head of Design at Gamma) shows how he uses AI as a research assistant to digest large volumes of messy, multilingual product feedback—about 550 responses in a week—without manually translating or sampling only a small subset.
Get the full analysis with uListen AI
How did you validate the deep research output against ground truth—did you sample rows to check translation accuracy and theme assignment?
He demonstrates using ChatGPT “deep research” to translate, summarize, and classify feedback by themes (what’s working, what isn’t, prompt patterns), then exporting those classifications for charts and team-ready reporting.
Get the full analysis with uListen AI
When you found multi-step edits failing, which UX intervention tested best: prompt splitting, follow-up questions, or showing an editable “plan” of steps?
On the brand side, he walks through a Midjourney-based workflow that uses style references/personalization to rapidly iterate toward consistent, art-directed imagery for UI “empty states,” plus Replicate models for fast background removal before dropping assets into Figma.
Get the full analysis with uListen AI
How did you decide which image models to use for people vs objects, given recurring issues like “extra arms/fingers”?
Finally, he shares a lightweight Claude “project” workflow to standardize job descriptions across hiring managers, and reflects on what human designers should keep owning: fun, personality, and craft details.
Get the full analysis with uListen AI
What does Gamma’s Midjourney “style kit” concretely include (SREF codes, personalization settings, banned words, example prompts, review process)?
Get the full analysis with uListen AI
Transcript Preview
About how many pieces of feedback did you analyze this? Is this dozens? Is this hundreds?
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 deep research on this file. The cool thing is, it sort of went through all the feedback, understood what's working, what's not working, what prompts work, what don't work.
Just having tools like this allow you to stay much closer to the customer, access large-scale research in a way that would've been very tedious and expensive before. I'm curious if you can tell us a little bit about how you use AI to scale brand and art direction.
What we have actually come up with here is an ability to use Midjourney as part of our workflow to help make our art direction consistent, and be able to come up with design elements way faster than before, and it's almost like I can follow those rabbit holes of creativity. I can be like, "Let me just explore this idea," and every one of those ideas feels like it could be something I could use.
You're able to bring this next layer of craft, and detail, and care to the user experience, which I do think makes a difference. [upbeat music] Welcome back to How I AI. I'm Claire Vo, product leader and AI obsessive, here on a mission to help you build better with these new tools. Today, we have a fun and inspiring conversation with Zach Leach, head of design at Gamma. Zach's gonna show us how he uses AI as a data researcher, user researcher, deep researcher, and art department, so he can focus on the craft, care for details, and fun he wants to deliver for Gamma's users. Let's get to it. This episode is brought to you by WorkOS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data, and even handle support tickets automatically. But there's a catch: these tools only work well when they have deep access to company systems. Your copilot needs to see your entire code base. Your chatbot needs to search across internal docs, and for enterprise buyers, that raises serious security concerns. That's why these apps face intense IT scrutiny from day one. To pass, they need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch, it's a massive lift. That's where WorkOS comes in. WorkOS gives you drop-in APIs for enterprise features, so your app can become enterprise-ready and scale upmarket faster. Think of it like Stripe for enterprise features. OpenAI, Perplexity, and Cursor are already using WorkOS to move faster and meet enterprise demands. Join them and hundreds of other industry leaders at workos.com. Start building today. Zach, thanks for being here.
Sure, no problem. Thanks for having me.
I'm such a big fan of the Gamma team. I'm such a big fan of the Gamma product, but what I, I love the most about what you've built, not only is a great AI product, but it is truly a global product. So how many of your customers are actually international?
Install uListen to search the full transcript and get AI-powered insights
Get Full TranscriptGet more from every podcast
AI summaries, searchable transcripts, and fact-checking. Free forever.
Add to Chrome