Snapshot · The MongoDB Podcast
ROX initially used AWS DynamoDB as its document store due to the founders' Amazon background, but migrated to MongoDB late last year when scaling demands required its additional features.
Where this was said
At 6:44 · chapter starts 5:10
Ishan walks through ROX's technical architecture in concrete terms, framing it as a three-layer cake. The bottom layer is the context system: a knowledge graph that aggregates all available data about customers, relationships, and business signals, governed by enterprise-grade access controls. On top of that sits what Ishan says ROX pioneered — the concept of agent swarms, an orchestration system where thousands to potentially millions of pre-built agents communicate and coordinate with each other to get work done. [1] — Ishan Mukherjee "Think of ROX as a three-layer cake: a knowledge graph and governance system at the base, an agent swarms orchestration layer in the middle …" 05:05 The top layer is the application surface: a web app, a mobile app, and integrations into platforms like ChatGPT, Microsoft Copilot, and Slack. He connects this architecture directly to MongoDB: the context system deals overwhelmingly with unstructured data — emails, call transcripts, meeting notes, news — the kind of data that traditional relational or CRM databases were never designed to handle at scale, and that document stores like MongoDB are purpose-built for.
ROX pioneered the concept of agent swarms — an orchestration system where thousands to millions of pre-built agents communicate with each other to complete tasks.
ROX started on AWS DynamoDB — the founders came from Amazon, so the choice was instinctive. But as scale hit, MongoDB's feature set and security profile pulled them over. Today it manages all of ROX's unstructured data: emails, call logs, transcripts, notes.
Sam's initial MVP was coded in approximately one week using ChatGPT voice mode and copy-pasting code, with no prior technical experience.
Sam argues Discord is 10x better than email for building relationships with younger users who rarely check their inbox.
Sam's monthly operating costs include Cursor ($200), AI image generation ($100), AI video generation ($200), hosting ($100), email marketing ($80), and AI compute ($300–$500).
Sam recommends copying days of Discord chat history into ChatGPT and prompting it to list recurring pain points as a fast, free market research technique.
Bhanu and his team built approximately 50 free tools to attract search traffic, each linked back to SiteGPT.
With AI coding tools like Cursor, Bhanu can now create a new free marketing tool in less than 5 minutes by referencing existing tools.
Bhanu filters Ahrefs keyword results to show only those with a keyword difficulty below 10, making them realistic ranking targets for any decent website.
Bhanu sets a minimum search volume of 1,000 monthly searches when selecting keywords to target with free tools.
PropGPT averaged 20 downloads per day right after launching on the App Store through influencer marketing.
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.