Podbit · The MongoDB Podcast
At ROX, there's no AI tool approval process — engineers use Cursor, Cognition, Claude Code, whatever helps. The whole company runs on ROX itself, with no other software. Eating your own dog food isn't a slogan here; it's the entire operating model.
Where this was said
At 11:20 · chapter starts 10:00
There's a philosophical debate in every engineering team about which technologies to adopt, and Ishan's framework cuts cleanly through it: separate the 0-to-1 question from the 1-to-scale question. [1] — Ishan Mukherjee "Technology stack decisions aren't one-size-fits-all — they depend entirely on what phase you're in. Early stage needs developer-friendly AP…" 09:50 In the 0-to-1 phase, what matters is developer experience — great APIs, no sales call required, easy onboarding, a strong community and brand. That's why ROX chose DynamoDB initially; it was familiar, fast to start with, and backed by AWS. The 1-to-scale phase asks different questions: can the architecture handle massive enterprise traffic spikes? Is query performance fast and reliable enough for real-time agent operations? Does the security model meet enterprise procurement requirements? MongoDB, Ishan says, is where ROX found its answers for that second phase — and he adds a note that MongoDB appears to be 'regaining its mojo' after a period when vector stores and other specialized systems were capturing developer attention.
Sam had no coding knowledge, so he used ChatGPT voice mode to generate his entire codebase and copy-pasted it into Notepad. A friend later introduced him to Cursor, and he never looked back.
Copy days of Discord chat history, paste it into ChatGPT, and ask it to list recurring pain points. The ones that come up most often are your best product bets.
Sam's top advice: when prompting Cursor, tell it to architect code for 100,000 users from day one. The AI changes its approach, building scalable frameworks instead of brittle one-user code.
With AI coding tools like Cursor, Bhanu replicates an existing free tool for a new keyword in under 5 minutes. What used to be a multi-day build is now a lunch-break task.
Ahrefs, SiteGPT, Cal.com, PostHog, Datafast, Sibyl AI, Bento, Feather, Featurepace, Mintlify, Cloud Code, ChartMogul — Bhanu runs his entire business solo with these 12 tools.
PropGPT runs on React Native with TypeScript and Python for ML, Neon for the database, RevenueCat and Superwall for monetization. LLM costs are $20/month, data APIs $100/month, and after $10K in monthly marketing spend, margins sit at roughly 50%.
Game apps keep users engaged long enough for ads to pay off. Tool apps don't — so if you're building a utility, ads are almost always the wrong call and subscriptions are your only real lever.
Inside SEO Bot, a single button labelled 'Boost My Domain Rating' routes users directly to Listing Bot. That one interaction converts a user of one tool into a user of two — without any marketing cost.
Directory listings are a powerful but underrated growth channel — but only if your product is genuinely interesting enough to earn the click. AI products have a natural advantage here because they're easy to package in a compelling, clickable way.
We use essential and analytics cookies to run Vuci. To understand how the site is used: Privacy Policy.
Install Vuci on your phone
Add it to your home screen for a faster, app-like experience.
Install Vuci on your phone
Tap the Share button, then “Add to Home Screen”.
A new version is available
Reload to get the latest Vuci.