I design and build AI products, end to end.

What I had to get right

• Three users, three sets of screens. Each role gets its own screens. Mixing user types in one view is a cost you pay forever.

• Floor plans in real-world units. The drawing tool works in millimeters, not pixels. Zoom in, zoom out, change a setting, and the math still works because the units are real.

• Locked-down database access. Two simple checks decide what each user can see. Every database change gets tested from two angles: the owner's view and an invited user's view. Catches the most common security bug in this kind of app.

• AI that suggests, never pushes. Drop a quote PDF in, get a project draft. Ignore every suggestion if you want. The AI offers; the user decides.

• Ten languages kept in sync. English is the source. Swedish is required. The others are best-effort. No raw text hardcoded into the screens, ever.

What I had to get right

• Idea to finished creative output in one pass. Key art, a themed reel, a generated soundtrack and sound effects come back together, styled to the same brief.

• Every piece re-rolls on its own. Keep the soundtrack, regenerate the art, flip between versions. That is how creative teams actually iterate.

• Several generative models behind one canvas: image, video, music and sound, each picked for what it does best, and the seams between them handled so the user never sees them.

What I had to get right

• AI drafts the product descriptions. The brand voice stays human.

• Every output is editable in one click. The cheapest fix for "AI got it wrong" is making it easy to fix.

• One source, many outputs. The same product data comes out as a PDF catalog, a live link or a wholesale linesheet.

What I did

• Commercial packaging. Translated technical capability into pricing tiers, contract terms, and value propositions partners could understand and buy.

• Demos that closed. Live walkthroughs with platform leads at editing tools, content platforms, and creator software. Knowing the product end-to-end meant I could answer technical questions on the spot, without escalation.

• The partner voice in the roadmap. Brought partners' real needs, the engineering cost and the risks to the roadmap and pricing decisions, and argued for saying no to a lot of requests so the API stayed sharp.

• Customer success at scale. Onboarded partners from cold inbound to multi-million-user integrations. The companies that scaled with us had a working partnership behind the integration.

• The bridge between commercial and engineering. Translated partner pain into engineering work, and engineering trade-offs back into language commercial leaders understood.

What I had to get right

• Everything the system needs lives as plain markdown in one place, including the corrections I've given it over time. If it isn't written down, the system can't act on it.

• When I drop in a screenshot of something to handle, it gets read, drafted into the right document and filed where it belongs, so the analysis and the legwork happen without me.

• The app is disposable and I rebuild it in an afternoon when my needs change, but the markdown underneath never moves, because that's where the value actually sits.

• It prepares and drafts everything, but I make the last call on anything that gets sent, paid or published. The loop runs on its own right up to the decision that matters.