MongoDB manages all unstructured data
ROX uses MongoDB as its core document store for all unstructured data sources including emails, transcripts, call logs, and notes.
Snapshot · The MongoDB Podcast
How Rox Is Rebuilding the CRM for the AI Era on MongoDB
Explore episode
Apr 28, 2026
Where this was said
From DynamoDB to MongoDB: The Migration Story
At 7:37 · chapter starts 6:50
The decision to use DynamoDB at launch was almost reflexive: both Ishan and Sriram, ROX's CTO and co-founder, came from Amazon and had deep familiarity with AWS infrastructure. For the 0-to-1 phase, that bias was fine — DynamoDB worked. But as ROX hit genuine enterprise scale, the team reached a point where MongoDB's feature set, scalability, and enterprise-grade security characteristics were meaningfully superior for their specific workload. [1] — Ishan Mukherjee "ROX started on AWS DynamoDB — the founders came from Amazon, so the choice was instinctive. But as scale hit, MongoDB's feature set and sec…" 06:44 The migration happened in late 2024, and MongoDB now serves as ROX's core document store, ingesting and serving the full range of unstructured data sources that feed into the knowledge graph. Ishan is careful to note this is an evolving relationship — MongoDB is a fast-growing part of a larger data infrastructure, not the entire stack.
Context system = key AI competitive moat
Ishan argues AI agents are only as good as the context they have access to, and most customer context lives in data warehouses — not in the CRM.
The Real AI Moat: Context, Not Models
GPT, Claude, Gemini — they're available to everyone. The actual competitive moat is who can aggregate, activate, and make their data agent-ready. That's the insight driving ROX's entire architecture, and it's why systems like MongoDB matter more than model selection.
Similar snapshots
MVP built in one week
Sam's initial MVP was coded in approximately one week using ChatGPT voice mode and copy-pasting code, with no prior technical experience.
Discord vs email for young users
Sam argues Discord is 10x better than email for building relationships with younger users who rarely check their inbox.
Monthly infra costs ~$780–$980
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).
ChatGPT-powered pain point research
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.
50 free tools built total
Bhanu and his team built approximately 50 free tools to attract search traffic, each linked back to SiteGPT.
New tool built in under 5 minutes
With AI coding tools like Cursor, Bhanu can now create a new free marketing tool in less than 5 minutes by referencing existing tools.
KD filter < 10 for rankable keywords
Bhanu filters Ahrefs keyword results to show only those with a keyword difficulty below 10, making them realistic ranking targets for any decent website.
Minimum 1,000 monthly search volume
Bhanu sets a minimum search volume of 1,000 monthly searches when selecting keywords to target with free tools.
20 downloads/day at launch
PropGPT averaged 20 downloads per day right after launching on the App Store through influencer marketing.
