Software for the manual work that shouldn't exist.

What the build forced me to figure out

• Three users, three sets of screens. Each role gets its own screens, not the same screens with parts hidden. 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.

• Five 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 it shows

• 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 this build is about

• AI handles the boring 80% of a product description. The last 20% is brand voice and 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 channels. Same product data flows out as a webshop entry, a spec sheet, a wholesale PDF.

What the role actually meant

• 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 who scaled with us did because the partnership worked, not because the API alone did.

• The bridge between commercial and engineering. Translated partner pain into engineering work, and engineering trade-offs back into language commercial leaders understood. That's where most API platforms fail.

What it proves

• 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, and that's the unglamorous part most companies skip.

• 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.