I Think in Text, People Need Visuals: On Hating Making Slides and Finding Tools That Help

One of my biggest pain points at work is slide presentations. I am not a visual person whatsoever. If I made the rules, I would be perfectly happy presenting in markdown—bullet points, tables, well-structured walls of text. That works for me. But apparently, this does not register well with people.

You are always in your own head with your own context. You think people will get you, but they really don't. You need to set the frame, the context first. Visuals are a great hook—they say a picture conveys a thousand words. That's why infographics work so well in capturing people's attention and conveying the message. The visual isn't decoration. It's the entry point that lets people into your thinking.

So I need to create presentations to communicate effectively. The dream process would be: structure all the text content (with the help of AI, as I figure things out, explore, and debate with myself), then hand it off to an AI to turn it into a beautiful, presentable slide deck. I'd rather outsource the part I don't like.

What I Was Looking For

I tested five tools: Kimi, Genspark, Canva, Notebook LM, and Skywork.ai. Here's what I was evaluating:

• Context understanding: Does it actually get what I'm trying to say?
• Visual quality: Are the infographics and layouts good enough to communicate?
• Editability: Can I tweak after generation?
• Time savings: Does it actually help, or does it create more work?

The Testing

Skywork.ai is extraordinary. The context understanding is almost on point—it gets what I'm trying to say and translates it into slides that actually make sense. The design is more than great; it's genuinely impressive. Editing works through prompting, which fits naturally into how I already work. The one caveat: detailed editing is possible, but not by default. To make granular changes, you first need to go through an image-to-code conversion step, which takes extra time and can slightly distort images and layout in the process. It's a trade-off worth knowing about, but it hasn't stopped me from using it. What pushed it to the top is that it gets the best of both worlds: it respects the information structure and order I give it—like Genspark—and the visuals are genuinely great. Neither of the others could deliver both at once. This is now my tool of choice.

Kimi looks beautiful—the templates are polished and professional. But some messages are lost in the translation from text to slides. When I reviewed the output, I realized it didn't fully capture what I was trying to say.

Genspark got the context. It's structured correctly, no message is lost, and crucially—it doesn't rearrange things. It follows the structure you give it. The visual polish isn't there, but for a real stretch of time this was my actual go-to. When I had a lot of information and a specific talking order I needed to preserve, Genspark was the reliable choice. I'd rather have the right structure with plain visuals than beautiful slides that tell the story in the wrong order.

Canva couldn't structure the presentation elements in the right context. The AI didn't understand how to organize my content meaningfully, which made it hard to use.

Notebook LM kept all contexts and added a little too much in places, but the infographics are beautiful. The context understanding is strong, and it genuinely helps communicate the message—partly because of the Gemini 2.0 Flash model underneath, and it shows. The catch is it can't be edited directly, and when I bring in a lot of content with a specific talking structure, it tends to shuffle the order. For a lighter presentation that's manageable, but when the sequence matters, that becomes a real problem.

So the journey went like this: Notebook LM for early wins, Genspark when structure became the priority, and then Skywork.ai.

The Reflection

Does this solve my problem? More than before—and now with a tool I actually want to keep using. Skywork.ai hits the combination I was looking for: context that's close enough to what I actually meant, design that I'm not embarrassed to present, and an editing model that works the way I think—through prompting. The image-to-code conversion step for detailed edits is a minor friction, not a dealbreaker.

What makes a "well-structured wall of text" actually good? Honestly, it's not. It's just easy for me—I don't need the extra step. I've seen it work in unique situations (like Amazon's meeting room etiquette, where preparation is a wall of text), but that's rare. I personally do not like creating visualizations, so it would be a dream scenario if I could just outsource that.

And now, I actually can. I can focus on my strength—structuring ideas, thinking through content, debating with myself through AI—and let Skywork.ai handle the rest. The part I hate is now handled by something that does it better than I would anyway.

Not perfect. But close enough to stop searching.