Graphic design company Napkin AI is carving out a unique path in an exciting frontier area of vertical AI agent applications.
A user can type some text in the Napkin AI’s web site, and Napkin generates a graphic that represents your text within five seconds.
What’s fascinating is that under the hood, Napkin is doing this by taking the different traditional jobs of a design agency — copywriter, designer, illustrator, brand stylist – and replicating those discrete functions with individual AI agents — instead of with humans.
The product has gotten impressive traction since launching in August. It has 2 million beta users, double the number of users just six weeks ago, according to Pramod Sharma, Napkin’s co-founder and CEO.
“We’ve taken a slightly different angle,” he said in an interview with VentureBeat. “We didn’t start with: ‘Let’s look at an image model and see what it can do.’ In fact, for us that was an afterthought. It’s really about what it takes to create a graphic, and how it’s done today, and work backwards.”
Napkin AI is part of a trend toward vertical AI agents
Napkin is part of a growing number of startups that are popping up to serve vertical areas with products that are not driven by the incumbent model of SaaS, but by vertical AI agents that are under the hood. Napkin shows how productive these agentic companies be. It is a team of 12 working remotely, with Sharma the only one living in the SF Bay Area. These companies also promise to be highly disruptive, because they are so much more customizable and powerful for their specific use cases.
For a deeper dive into Napkin AI’s approach, including insights from its co-founders on how their agentic system works, check out my conversation with Sam Witteveen, an AI agent developer, and the Napkin team in this YouTube video:
What seems to set Napkin apart from the competition in its own space is its focus on serving a specific need: Helping professionals who aren’t graph design experts to create pretty designs, mainly for PowerPoint presentations. These users want diagrams and other illustrations, and not just the slick images produced by a lot of generative AI providers — and they want to be able to edit these images easily and simply. And that’s what Napkin does: After providing its best shot back to the user within five seconds, it lets the user edit it for things like style, color and design type. (See image below for example of an image rendered by Napkin)
Napkin AI represents a third way
Napkin doesn’t use diffusion AI models used by most other image providers, CEO Sharma said, because those models don’t allow users to easily edit unique elements of illustrations, for example the slices of a pie chart, or surrounding text. By undergirding the Napkin product with agents that serve specific, useful functions, Napkin’s approach represents a “third way.”
The “first way,” taken by incumbent graphic-design contemporaries like Adobe or Canva, is to bolt AI tools onto traditional design workflows. Napkin doesn’t do this. It is generative AI-first, in that it uses generative AI to create the best visual first-draft that it can, based on a user’s prompt. It then simplifies the remaining editing process, keeping in mind that most users don’t have advanced design skills — the kind you need, for example, to figure out Adobe Creative Cloud.
Neither is Napkin following the “second way”, that of the new breed of AI image and video companies, like MidJourney, Stable Diffusion, Runway, Ideogram, and others — that pride themselves on being AI-first, and use massive diffusion models to bamboozle users with high-quality images or videos. It’s often not clear how they differentiate from each other. Napkin, however, is determined not to fall under the swoon of marvelous technology for the sake of it, because that doesn’t put users first, Sharma said.
Here’s how Napkin AI works: It allows users to paste a text description—whether it’s a presentation prompt, a blog excerpt, or brainstorming notes—and receive multiple high-quality graphic options in seconds. These graphics are not mere templates but customizable designs, with editable fonts, colors, and layouts — but they are easy to use, with sliding tools. The product eschews the huge menu bar with the hundreds of options provided by more complex tools like Figma or Canva. After creating an image, Napkin allows you to export it in an PNG, PDF or SVG format.
Napkin AI has four sub-agents under the hood
More interesting, though, is how the agents are working under the hood: Napkin uses an orchestrator LLM, driven mainly by OpenAI’s GPT-4o mini, to respond to a user’s prompt. This LLM acts as an agent, delegating jobs to a series of other sub-agents that have specific responsibilities. The first “text” agent suggests some text that can be used in the design. The second “layout” agent looks at the text, and decides on a specific design layout that would be best for that text. A third “icon and illustration” agent checks a database to see if there’s an icon that matches the text request, and if there isn’t, it might generate an icon on the fly. Finally, there’s a fourth “style” agent, which lets users customize the design with their own corporate colors and style. As CEO Sharma explains it, Napkin doesn’t put too many constraints on these four agents, other than to maximize for quality and speed. Responding within five seconds is key to delighting customers, Sharma said.
Each “agent” contributes to the overall composition, ensuring the generated graphic is not only aesthetically pleasing but tailored to the user’s intent.
The fourth, “styling” agent will be introduced into the product next week, and there will be improvements over time, Sharma said. Soon, users will be able to upload a screenshot or other documents of their corporate styling, so that an image model can automatically generate images in that style. He cited the research being done by Meta in the area of large concept models (LCMS) that could help here. For now, though, Napkin’s agent is a rendering engine that offers various styling options to users via a dashboard.
Quality and focus as differentiators
One of Napkin’s most striking commitments is its focus on quality. For Sharma, the goal isn’t just to produce visuals quickly — it’s to ensure every graphic is worth using. “We take your written content and transform it into a graphic that truly captures the essence of your idea,” Sharma said. “We realized that in a graphic, good is not enough. It has to be really, really great. Otherwise it defeats the purpose.”
Sharma co-founded Napkin AI with Jerome Scholler, after sharing a joint frustration around the quality of presentation decks. Before starting Napkin, Sharma built kids’ educational games company Osmo, which was also known for design quality. Scholler was also part of Osmo’s founding team. Sharma is also an ex-Googler.
This obsession around quality extends to the technical underpinnings. Unlike diffusion models that often lack semantic understanding of graphics, Napkin’s agent-driven platform allows it to separate elements like content, layout and style. This decoupling allows users to modify content dynamically without losing the design’s integrity.
Traction and expansion
The market seems to agree with Napkin’s approach. The platform has doubled its users within the past six weeks, and is showing strong retention rates, suggesting that users like the underlying workflow. After a few weeks of use, “users are like: ‘Give me more!’” Sharma said. “‘Can you expand the catalog? The possibilities? The type of illustrations?’ It’s good for us because we are very focused now.”
What’s interesting, though, is that for visual communications, certain designs work well, and others don’t. The human brain can easily understand pie and bar charts, for example, but can have a harder time with other designs. “What we have learned about the space is that the structures themselves are not unlimited,” Sharma said. “They’re well-defined structures or metaphors that people typically use, but how do you render them? How do you illustrate that metaphor? That’s where a lot of creativity comes, and we are actually working on expanding that dramatically.”
The company raised a $10 million seed round in August, and came out of stealth at that time (see VentureBeat’s coverage at the time). But it has been three years since they started working on the problem. “I can tell you it still is really hard problem,” Sharma said. “Humans are so good at reading graphics, and figuring out if the graphic is good. They don’t know how to make one, but they can judge one very, very quickly.”
The future of Napkin AI
As larger players like Canva and Adobe eye the generative AI space, Napkin AI’s clear differentiation could make it an acquisition target. Whether as an independent disruptor or a critical component of a larger ecosystem, Napkin AI is undoubtedly one to watch in the generative AI graphics landscape.
The post Napkin AI’s ‘design agency’ of AI agents is changing how professionals create graphics appeared first on Venture Beat.
