DEV Community

Cover image for We built a desktop AI app with a $0 ad budget. Here's what worked (and what didn't) in the first month
BrainWave Studio
BrainWave Studio

Posted on Edited on

We built a desktop AI app with a $0 ad budget. Here's what worked (and what didn't) in the first month

We're BrainWave Studio, a tiny independent studio. This month we've been shipping Valaris — a Windows app (plus a web version for phones) that puts hundreds of AI models into one chat. You bring your own OpenRouter account, you see the price of a request before you send it, and your chats stay on your device.

No funding, no ad budget. Here's what we learned so far.

Why we built it

Paying for five AI subscriptions to use each model a few times a month felt wrong. Pay-per-request through one API is usually much cheaper — but the existing tools either hid the price, stored your chats on their servers, or were built for developers only. We wanted something a normal person could install and use.

What we shipped in the first month

  • Releases 1.5 → 1.6.3 — an update every few days, each one built and checked by our own pipeline (the app installs updates only after verifying our signature).
  • Agent mode — the model creates files, runs code, opens the page it built in a clean browser window, takes a screenshot and fixes what it sees. On a cheap model, 10 real projects cost $2.00 in total.
  • Valaris Hub — 30 ready-made skills (CV, business plan, SQL, homework help, trip planning). 3 free, all with Pro.
  • A site in 9 languages — 459 pages, each skill and each project with its own page.
  • ~480 automated tests — boring, and the reason we can ship every few days without fear.

Decisions that saved us

  1. Python + the system web view instead of Electron. The installer is ~17 MB, and all the logic lives in one language.
  2. Licences without a licence server. Pro codes are signed with Ed25519 and checked offline. Nothing to host, nothing to go down.
  3. No user data on our side. Chats live on the device; we never had to build (or secure) a database of other people's conversations.
  4. Safety rules for the agent from day one. It only sees folders you pick, every write shows a diff and asks first, every change can be undone, and there is no delete at all.

What didn't work (yet)

  • Payments. Card payments for a small studio are hard; we started with Telegram Stars through our own bot. It works, but it's an extra step for buyers.
  • Unsigned installer. A code-signing certificate costs ~$120–170/year, so for now Windows shows a warning on first run. We know it costs us installs.
  • Building before telling. We spent weeks shipping before writing a single post. Our first article went out only this week — we should have started much earlier.

What we're trying now (all free)

  • Articles where the audience actually is: a business story on vc.ru, an agent/code story here on dev.to, a technical deep-dive on Habr.
  • Search: sitemap + Google Search Console, Yandex Webmaster, and IndexNow, so new pages show up in Bing and Yandex in minutes, not weeks.
  • Skill and project pages that answer real searches ("AI resume writer", "AI business plan") in 9 languages.
  • Product Hunt in early December.

Ask

If you've launched a desktop app without a signing certificate — did the Windows warning hurt you, and when did you buy one? And what was your first channel that actually brought users?

Links, if you want to look: valaris.app · the 10 projects the agent built: valaris.app/portfolio · every release with SHA-256 checksums: GitHub · our previous post: A cheap AI agent fixed 7 bugs for $0.01

— BrainWave Studio, the team behind Valaris

Top comments (0)