Building AI-to-Physical Products

The Gap

AI generates content easily. Claude can write a project status update in seconds. ChatGPT can summarise a meeting transcript instantly. The content is there.

But turning that content into something professional—something you can print, present, hand to a client—is still tedious. You copy from Claude, paste into PowerPoint, fight with formatting, adjust margins, fix overflow, wonder why the columns don't balance.

That gap is where I build.

AI generates content easily. Turning it into professional physical output is hard. That's the gap.

The Pattern

Every product in this portfolio follows the same pattern:

User generates content      →    Tool processes          →    Physical artifact
(in Claude/ChatGPT)              (deterministically)          (slides, PDF, etc.)
     ↓                                  ↓                           ↓
  They pay for AI               You pay nothing              You charge for value
  (or free tier)                (no AI costs)                (convenience, quality)

I call this BYOAI—Bring Your Own AI. The user already has Claude or ChatGPT. I don't need to bundle AI and charge for it. I just handle the formatting.

Why This Works

No AI costs. I'm not calling OpenAI or Anthropic APIs. The user's AI generates the content; my tool just formats it. Margins stay high.

Deterministic output. Same input = same output, every time. No prompt engineering, no model drift, no "why did it do that?" debugging.

Physical correctness is hard. Fold lines that actually align when printed. Columns that balance automatically. PPTX files that are editable, not images. This is the kind of thing AI tools do poorly—and the kind of thing traditional tooling does well.

The Portfolio

TriFold PDF was the first. Paste AI content, get a printable tri-fold reference card with proper fold alignment. One-time purchase, validated the pattern.

DeckEngine is the current focus. Markdown to editable PowerPoint with automatic two-column balancing. The layout engine uses Typst—40 years of typesetting algorithms that no competitor can easily replicate.

What's next? Exploring church bulletins (52x/year recurrence) and name badges (Avery sheet layout math). Same pattern: AI content + physical formatting = value.

The Criteria

Not every idea fits. Before building, I check:

• Recurring need? Monthly reports beat one-time spice jar labels.
• B2B or prosumer? Businesses have budget; consumers are price-sensitive.
• Technical moat? Column balancing is hard. Text on rectangles is easy.
• 2-week MVP? Ship fast, validate, iterate or kill.

The goal isn't one big product. It's a portfolio of small, focused tools that each do one thing well—and share infrastructure underneath.

If you're building something similar, or have thoughts on this approach, I'd like to hear from you.