Blog

Imagine a design environment where there are no defined rules to follow and infinite experimentation is encouraged. This is the space in which Tome’s product design team works as they build a new kind of 

 with AI for millions of professionals around the world.

Product designer at Tome, Shannon Rhee, shares her thoughts on designing a novel AI product for the workplace where large language models (LLMs) are taught to generate endless types of outputs, and how to navigate a design world with infinite possibilities.

Tome: From a design standpoint, what’s been most challenging, or surprising to you, when working with LLMs?

: When you’re designing for a nondeterministic system, you have to relinquish some level of control and precision that you’d otherwise have with traditional product design—how do you teach an LLM what a good layout looks like, what typographic rules exist, and what best practices to adhere to?

These are not easy questions to answer and are exciting challenges that the Tome design team are tackling on a daily basis.

Tome: As a product designer, how is AI changing the way you work?

: It’s not only changing the way we work with AI, it’s also changing how we 

 AI. In terms of visual and product design, it’s all about how we build the software and also think about the visual and experiential aspects of Tome specifically. What do the interactions between the UI and the UX look like?

Shannon Rhee

Product Designer, Tome

We think about collaboration in terms of understanding what’s possible and how it transforms Tome’s product. There’s a level of serendipity that we constantly deal with, because with AI, you’re never 100% sure of the outputs you’ll get. But that’s also liberating and where the innovation comes in.

Tome: What are some specific things that you and the team keep top of mind when it comes to weaving in principles of design with AI?

: There’s a certain element of surprise that you learn to get more comfortable with as a designer when working with AI. We’re guiding the LLM to generate dynamic layouts by teaching it the purpose of specific layout types.

Designing for AI requires acknowledging that the way a user engages with the product can yield significantly diverse outcomes — we have to embrace and design for flexibility. We analyze why things might be happening and make small adjustments and then we iterate and evaluate over and over again.

We’re playing with optionality and the levers we have to control the output—It’s like adding a bumper to lanes in a bowling alley; you put in guardrails and provide instructions to guide it.

Tome: Anything you’re most inspired by when it comes to AI and design at Tome?

: It's a fun time to look for inspiration in AI products today. Because the space is evolving so quickly, design paradigms have yet to be established in a formal way. We’re seeing new workflows for AI actions and existing patterns being re-purposed for new interactions.

The excitement of being a part of Tome’s design team stems from our persistent, design-centric engagement in machine learning experimentation. As a product design team, we’re constantly evolving our thinking and approach as the space matures.

For more on how Tome is pushing the limits with AI and machine learning, check out a conversation with our engineering leaders on the 

to get the latest in product news and features, and as always—drop us a line at 

A Tome Product Designer Navigates Building with AI's Infinite Possibilities

As AI becomes a more common professional tool, how can engineering teams make AI even more useful within the workplace? Tome’s engineering leaders had this top of mind as their teams explored new ways to give millions high-quality AI experiences, which led to 

We sat down with our head of AI, Ves Stoyanov, Archana Sankaranarayanan, engineering director, product engineering, and Sarah Sachs, engineering director, machine learning and infrastructure, to learn more about the tech behind generative presentations V2 and how it’s pushing the limits of generative AI at Tome.

Tome: What were the primary elements in our original generative presentation experience that the team wanted to update?

: There were a couple key elements that were top of mind when we set out to revamp generative presentation. First, we knew it was important to deepen interactive editing and advance the capabilities of the toolbar. 

Second, we wanted to give users more control in building their presentations by giving multiple ways to direct page information and design. People now have additional control and versatility in their narrative output.

Tome: How was machine learning used to accomplish this?

: We took a more advanced approach to working with LLMs (large language models). We needed to help train the model on the fundamentals of what powerful expression and compelling communication looks like.

We also thought about how to separate the actual presentation content creation from how you present the content. What are different presentation layouts that would be compelling? What combination of tiles and objects can we put together in the presentation structure that would enable better storytelling?

Asking for a range of strong approaches to page creation and content creation instead of relying on one deterministic information structure was vital.

Tome: Let’s zoom out a bit from generative presentations. Why is generative AI and machine learning at Tome particularly intriguing  and key today?

: What’s really exciting is that both are core to the entire infrastructure here at Tome. We are building things where every feature can be ingested by our AI systems, and be easily maintained. That is rare. There are many legacy institutions out there where to build like we do, it's just harder. Tome is uniquely positioned to leverage AI and machine learning at any point of the creation and honing process.

: We’re pushing the limits of LLM engineering and simultaneously deepening the work on our own models. We’re powering pages, and soon will be powering presentation generation with our own models. That’s an opportunity to further hone and refine narrative outputs, which can make the AI experience for people faster, more reliable and more seamless.

We also use a proprietary structure to communicate with the LLM—we call this format, TIF. That's a way for us to communicate narrative structures back and forth between the LLM and Tome’s back end.

: Generative AI and machine learning is fundamentally changing how humans interact with computers. The opportunity to continue expanding, exploring and pushing the boundaries of what we can do with engineering and in Tome, because it’s an AI-native platform, is incredibly exciting.

As both Ves and Sarah have mentioned, building the tech for even more interactive and iterative co-creation at Tome is a very unique opportunity. Generative creation in the tool is just another illustration of why it’s so powerful to create software fundamentally rooted in AI and ML, where all our systems can understand and converse with LLMs.

Tome: Thank you all for taking the time to share your thoughts with us. We’re excited to see what’s next from your teams!

For more tips on how to create your best work with generative presentations V2, check out our 

You can also get additional thoughts from 

 on all things AI and engineering here at 

As always, drop us a line with any questions at 

Training Models at Tome: How Engineering Leaders Push the Limits of Machine Learning & AI

There’s never enough time to produce polished, nuanced work that packs a punch. That’s why we’ve given Tome’s generative presentation experience a revamp so you can shape and express your ideas more powerfully, with even more control.

We’ll share ways to create great starting points with AI, delve into the new presentation experience, and share specific examples of how to use Tome for any presentation need, whether that's sales, marketing, or for an entrepreneurial endeavor. Let’s jump in.

Before honing your presentation, create a strong starting point with an effective prompt. You can begin with a 

brief prompt (think a sentence with a few details), or write complex prompts (a few sentences with more context)

From there, Tome’s AI lets you quickly generate outlines to help you refine your points. You can easily reorder or remove sections in the outline phase until you shape what works for you.

Now that you have some background, you’re ready to begin creating  content and building on your ideas. Here’s how to get started:

You can specify the desired number of pages in your prompt, i.e., "Create a 7 page presentation about..."

Wait a moment as Tome's AI creates the outline for your presentation.

If you like what you see and are ready to view the full presentation right away, tap 

But if you're seeking different ways to express your presentation visually, this is where the (new) magic  happens. In V1 of our presentation experience, Tome offered only one standard format for every page. Now in V2 of the presentation generation experience, you have multiple ways to direct page information and design. 

You can also refine your presentation with even more specificity page-by-page. Here’s how:

After your outline has been generated, tap the magenta 

Tome’s AI generates four different page options.

Select the page content layout and design you like best.

 → to get four new options to choose from, select one, and continue page-by-page until you’re finished.

You’ll know the draft is done when the magenta 

For deeper dives on tips for presentation creation, check out our in-depth guide, 

How to Create a Great Presentation with AI in Tome

Let’s dive into a few examples of how to use presentation prompts in common use-case scenarios.

In this example, a founder of a pet hardware company uses a short but precise prompt. He asks for a 

 that describes the type of hardware that the company offers: point-of-care devices.

The page layout features an all-text with single hero image option. A large text tile on the left showcases a placeholder company name in header font size so it’s easily readable.

The text tiles on the right organizes an overview of their sample product information using simple, clear headers and paragraphs of content.

Tome’s AI can capture long and detailed prompts as seen in this Sales-focused example around block chain tech and supply chain management.

There are three distinct requests in this prompt. They ask for an outline, discussion points for the topic, and specific examples in the form of case studies.

This is an example of a conclusion page. A compelling visual image is generated that draws the eye in and anchors the columns of content with headers that organize the clear, concise nuggets of information that addresses the prompt.

From the perspective of a marketer building a presentation around virtual reality, this is another example of a more contextual and detailed prompt.

Multiple requests are in this prompt—they want info on current trends in VR for an educational setting, examples of ways to use VR, and a nod to how it might be beneficial for future generations.

In this layout option, Tome’s AI aligns a captivating single image alongside supporting content. The information is organized using a straightforward header font and body copy formatting paired with a bulleted list view for easy readability.

This freelance travel creator is in the beginning phase of creating a presentation, and uses a sentence with a few instructions as a prompt.

Tome’s AI quickly generates detailed content that hits each prompt keyword and formats it in a digestible format—header and supporting paragraph.

In this layout option, visually stunning AI-generated images that offer a different glimpse into luxe travel compliments the body of content in the presentation’s page.

We hope generative presentations V2 gives you more narrative control and greater impact in work and in life. For more tips and best practices on how to create in Tome, be sure to bookmark our 

You can also experiment on your own and start a presentation in Tome from scratch. For even more inspiration, check out our growing 

 to find strong thought-starters for your work.

As always, we’d love your feedback. Drop us a line at team@tome.app.

Meet Generative Presentations V2: How to Make Your Best Work in Tome

Sarah Sachs is Tome's newest engineering leader who oversees our machine learning and infrastructure teams. Her focus is on building cutting-edge systems that provide high-quality AI experiences for millions of professionals. 

We sat down with Sachs to learn more about how generative AI is core to Tome’s building principles and how the team plans to incorporate deeper personalization across enterprises. 

Tome: When it comes to engineering and generative AI at Tome, what are you most excited about working on?

From an engineering standpoint, I’m really excited that generative AI is a core principle of Tome. Generative AI is a tool that’s accessible to everyone, but engineering organizations are still working on how to build for that. LLMs (large language models) offer a new schema of speaking between systems and move so quickly. How do you build an engineering infrastructure that can keep up, maintain your product’s quality, and lets you quickly iterate?

We now have the technology to learn more and use it in a way that helps our users. Tome has a great opportunity to help people get started making work faster and communicating their ideas without getting too fixated on form.

Tome: What did you work on before joining us?

I led the generative AI and natural language processing teams for the machine learning groups at Robinhood. As we were developing generative AI internally, I adhered to the principles of efficiency—there’s so much work to do in generative AI from that perspective, and figuring out how to help people get done what they actually 

Before Robinhood, I worked on personalization at Google. I learned many good lessons, including how to build robust pipelines that are safe and secure. I also learned how to extract beautiful insights in a way you can’t without the scale of a huge engineering enterprise. It’s something I’m excited to see Tome digging into as well.

Tome: Can you share what you find most impressive about the engineering work being done at Tome?

: From a technical viewpoint, I see such value in what the machine learning and infrastructure teams are building at Tome. There is so much green field from a development perspective when it comes to generative AI. When we say we’re an AI-native product, that’s not just a tagline. AI is integral in everything we do and how we develop. English is the new programming language.

Tome is a company that prioritizes generative AI as a core business value prop. As an engineering leader, that is a total gift, and also one of the most impressive things that you can work on in this industry right now.

Tome: How are you thinking about personalization in engineering from an enterprise perspective?

: Something I’m excited about here at Tome is thinking about how we can make a tool not just for individuals to share ideas, but for groups of people on a larger scale. How do we help teams work together and reduce the friction that can come from collaboration? Can we change the culture around how we share ideas? This is very rich ground to tap into on a deeper level.

When it comes to contextual understanding, we have so much power from which to build on. Generative AI is powerful because it takes general knowledge and applies it to a specific context. There are so many places in different enterprises and teams where that context is very specific. 

I’m excited to figure out how we expand into helping enterprises use Tome and make it so teams can clearly, effectively, and beautifully share their ideas and collaborate.

Sarah Sachs

Director of Machine Learning and Infrastructure, Tome

Tome: What is top of mind for you when it comes to building an effective engineering culture?

: Having a culture where everybody is able to bring their best selves to work and freely express their opinions is key. Being able to collaborate and learn from each other in a low-ego environment with the shared mission of doing what’s best for the company, the team, and doing what’s best for our customers are all factors I keep top of mind.

It’s easy to take that for granted, particularly at later stage companies where poor culture can be hard to reverse. I’m grateful that every day at Tome, in every meeting we have, we’re thoughtful about why 

 we’re doing what we’re doing, and ensuring everyone in the room is aligned and supportive of one another.

 to learn more about the people behind the page. For more on what’s new with Tome, bookmark the 

How Tome's Head of Machine Learning, Sarah Sachs, Thinks About Generative AI and Eng Collaboration

Meet Archana Sankaranarayanan, who joined Tome to lead product engineering. Archana leads our growing team of world-class product engineers who are focused on exploring new ways to use AI for idea creation, and building polished narrative-centered content for work.

We sat down with Archana to hear why she’s excited about Tome, where she thinks generative AI is headed, and what helps foster innovative, strong engineering teams.

Tome: Tell us more about what brought you to Tome?

It's an exciting time to work with this incredible team. When I used Tome for the very first time, I was thoroughly impressed by the UX, the polish, and fit and finish that you got right off the bat using the product.

As I started using Tome more and more, I realized that I was focusing less on the medium itself, and more on the content that I was creating, and on the ideas I was trying to express. That was absolutely fascinating to me, and from there, I was fully on board.

Tome: Can you share more about your work previous to Tome?

I led the engineering team responsible for Google Assistant, an AI-powered virtual assistant. I got to work specifically on the human-bot interaction aspects of Google Assistant—defining the tone, character and personality of the assistant.

Prior to that, I built content discovery and tagging software at Netflix, and scaled the engineering team at Open Sea, the world’s first and largest web3 marketplace for NFTs.

Generative AI continues to be an evolving topic of conversation. What are your thoughts on the future of AI as a whole?

: Generative AI allows for a new computing paradigm so to speak. The possibilities are limitless. We can automate ways of doing things that previously only humans could do. That said, automation is still rough around the edges and there are definitely issues when it comes to quality.

I think one compelling question is, How can we get to a place where the tech can resemble a human being generating versus an AI generating? To me, that's what's absolutely fascinating to sink our teeth into in terms of engineering.

Tome: Where do you think we are today when it comes to AI specifically with regards to the user experience and user interfaces?

: When it comes to both UX and UI today, we interact with chatbots, and that’s just the beginning. The interplay between generative AI and what's possible with UX patterns is enormous.

Getting to be a part of that, particularly right now, is very, very intriguing to me. You know, I hope it intrigues a lot of engineers out there, and that it also gets design and product folks excited.

Why? Because collectively, we get to shape this vision of how we can create and enable many interaction patterns. How humans interact with computers is going to fundamentally change, and go well beyond the chatbot UI of today.

There's so much room for us to explore and push the boundaries on what we can do with engineering. The opportunity is incredibly expansive. There's a place for literally every discipline within the product engineering and design communities to come and shape, and make meaningful contributions.

Archana Sankar

Director of Product Engineering, Tome

Tome: What is your outlook on building strong engineering teams?

: First, I've been so impressed with the engineering quality here at Tome—it's top notch. Secondly, it’s refreshing to see how the engineers are hyper-focused on the user experience. Engineers are also super passionate about having AI be an abstraction layer where it's more natively enabling the product experience, rather than it being a wrapper on top. I think it’s quite inspiring.

The blistering pace at which this industry is moving and advancements to generative AI makes it critical for engineers to keep abreast of what the community is up to. Participating in regular hackathons and conducting quick demos regularly that bring people together is crucial. Sharing our experiences and what we’re learning is a huge part of building and maintaining a strong engineering culture.

Meet Archana Sankar: Product Engineering Leader at Tome

What if you could skip the tough parts of starting something from scratch and get right into your creative flow? Whether you’re a marketer, founder, creator or leading a sales team, Tome’s AI gives you the flexibility to create a wide range of starting places for your work. From there, you can build, shape, and sharpen your narrative points.

We’ll cover the key ways for using Tome’s AI to rev on your ideas quickly and take them to new heights. Let’s jump in.

To begin, create a new tome by clicking the magenta 

 button in the upper right corner of your workspace. To unlock generative creation in Tome, hover your cursor over the gray command bar at the bottom of your tome.

From here, you can create a starting point for your work through a few different ways:

 and full, first drafts of presentations that you can edit and customize with the help of AI using the 

 feature to copy up to 25 pages of text into Tome and generate a synthesized, structured narrative in seconds.

 in your workspace on our site for even more ways to start great work. Last, you can always simply experiment and start building a tome from scratch.

Developing robust narrative frameworks in Tome begins with writing prompts. Learning how to craft the most effective prompts to shape the most compelling output with Tome’s AI is key. Here are some tips to keep in mind:

Whether you’re opting to create a multi-page narrative through “create a presentation,” or a single-page tome like a one-pager or landing site “with create a page,” start by specifying your use case or creation type. 

The use case options are endless—you can choose any format for work—

—or opt for personal and creative content such as an 

 from a birds-eye view and go broad to start, e.g., “a brand strategy for an e-commerce company,” or, “tips for a medium-sized sales team.” This is particularly helpful if you’re looking for thought-starters to kickstart inspiration.

Then you can be direct and specific in asking for what you want, as you would with a business partner or colleague. For example, say you’re seeking ideas for “a full-funnel go-to-market strategy featuring a mix of digital ads and out of home event ideas for a children’s clothing company.”

Let’s look at an example of a prompt when creating a presentation. Type this prompt into your command bar at the bottom of your workspace: "

enterprise sales pitch for environmentally friendly HVAC systems."

The ability to reorder your outline sections is done simply by dragging and dropping where you want your points to land.

You can also add or remove narrative sections by hovering over an outline item and clicking the 

icon on the right side of the section to add or remove any topic.

For even more tips on creating starting points with AI, check out our 

Tome 101 guide for creating presentations

Sharpening your ideas and elevating them with Tome’s AI is a powerful starting point because it behaves as a truly 

Tome’s AI considers all of your ideas quickly and uses them as jumping off points, providing additional context and narrative thought-starters in seconds. Whether you’re making a single-page narrative or a multi-page narrative like a presentation, it’s a seamless process.

You can then continue to refine by manually editing, tweaking and customizing your tomes. Here’s a breakdown of options featuring generative and manual features:

If you have a clear sense of your topic already, use 

 for additional inspiration, context and key narrative elements.

To better support your presentation points quickly, click the 

 button in the lower left of your workspace to view a range of layout options.

Choose the layout you prefer, or tap the 

Curating and selecting the right visuals is a huge part of the honing stage. Click on the 

 to the right of your screen and tap the Image tile.

button and enter a prompt—go broad or get granular. You can continue to riff and tweak your prompts if you don’t love the AI-generated images you get. You can also upload your own images, or select stunning, hi-res visuals from 

Most of us talk to our friends differently than we do with our bosses. Shifting our tone and style can be done in Tome within seconds using the ✨ 

Rewrite (highlight the text you wish to change and get a swift rewrite—

Adjust tone (select any text and choose from five different inflections—friendly, persuasive, neutral, etc.).

Reduce (highlight any text you want to see shortened).

Extend (select text to expand your sentences and thinking).

You can bolster or cross-check your arguments without leaving Tome, through 

Tome’s AI then searches every page of the internet, curating only the most relevant, high quality sources for your review in a new tab.

Remember that refining with AI doesn’t have to be the end of customization. For more on how to customize colors, themes and other features in the tile selector, check out our 

Tome’s AI is designed to help unlock and spark your creativity. We can't wait to see where the page takes you. Stay tuned for more in the 

What would you like to do more of with Tome? Let us know at 

Unlocking Your Ideas with AI in Tome

Emily Koh is the founder of PINKIES UP, a natural wine consultation, curation, and event planning and production company. What started simply as pop-up events—the first hosted on her front lawn—is now a growing business that collaborates with restaurants, bars, and private clients throughout Los Angeles.

Emily Koh

Founder, PINKIES UP

As a business owner, Emily must do more than keep up with natural wine and drinking trends. She also has to focus on constant brand building and training the service staff to bring that brand to life. This is crucial but time-consuming and repetitive. So Emily set it on autopilot by creating a sleek and professional 

that reflects PINKIES UP’s modern aesthetic. 

The tome serves double duty as an introduction to PINKIES UP and as an employee training guide. “It brings a level of creativity to something so functional,” says Emily. With the time her tome frees up, she’s able to focus on other parts of her business.

We sat down with Emily to learn how she built her guide and how it’s helping her grow PINKIES UP.

 has the same clean and bright energy as the 

. How easy was it for you to mirror that?

: The templates have been a game changer. I remember when I first started putting together 

, I'd look up examples on Google and model mine after them. So I love that so many built-in 

 exist in Tome. I don't need to spend unnecessary time working on the formatting of my decks and proposals and I can focus on the content instead. 

Everything you need to start creating is in your Tome workspace.

Sign in, and click the Templates tab on the left of your workspace to explore.

, there's a template for every storytelling, creative and business need.

 Once you’ve picked your template, make it yours. Go to the toolbar on the right side of your workspace to:

Change font styles and background colors.

Upload photos, search Unsplash’s library of stunning, hi-res visuals , or have Tome create an AI-generated image for you.

Resize photos, add tables, or change the layout with simple drag and drop.

Use dynamic tiles to add any type of content—text, images, video, Giphys, embed website pages, integration tiles featuring Figma, Airtable and Miro.

Go to the bottom of your workspace, click the command bar, and select

 to see a menu of 8 layout options. Remember, you can also customize to get it just right.

Tome’s still got you. You can use all of the same features to create a tome that's entirely unique. To get started, click the 

button in the upper right of your workspace.

Tome: Did you use any of Tome's AI features for content creation?

: Writing is actually the part that I enjoy the most because I feel that a big part of the brand power behind PINKIES UP lies in our tone of voice. But when I’m short on time and I need a more professional way of saying something, then AI does it.

Tome’s AI can be your thought partner, creative collaborator, ghostwriter, or editor. Create outlines, first drafts, starter copy, or full presentations.

After you’ve created a tome, you can create a starting point for your work through a few different ways from the command bar:

to rewrite, adjust the tone, or to fix spelling and grammar. Highlight the text you want to work with and select AI Edit from the toolbar that pops up.

to enter a prompt and get variations with different designs, text, images. Each will have a different approach to your topic.

to enter a prompt. Use the slider to select the number of pages you want and Tome will create a presentation for you.

 for using AI in Tome to unlock your ideas.

Blog

A Tome Product Designer Navigates Building with AI's Infinite Possibilities

Training Models at Tome: How Engineering Leaders Push the Limits of Machine Learning & AI

Meet Generative Presentations V2: How to Make Your Best Work in Tome

How Tome's Head of Machine Learning, Sarah Sachs, Thinks About Generative AI and Eng Collaboration

Meet Archana Sankar: Product Engineering Leader at Tome

Unlocking Your Ideas with AI in Tome

How Natural Wine Expert Emily Koh Grows PINKIES UP with Tome

The Basics of Tome: What it Is and What's Possible

How to Create a Great Presentation with AI in Tome

Creator Spotlight: metahaiku

Tips to Get the Most Out of References

How to Craft Prompts for Page Generation

Tips for Crafting Generative Prompts

The Magic Behind Tome's Color Algorithm and Themes

Tome Pro: For limitless creation and sharing

Craft your next great idea.