The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
What if anyone on your team could ask your data a question and get a live dashboard back in under a minute?
That was the brief. Business users were locked out of their own data. Every question waited on someone who could write SQL, data sat across disconnected systems, and security teams refused to send sensitive records to third-party AI tools.
So we flipped the model. Instead of moving enterprise data to an AI product, we moved the AI analytics product into the customer's AWS account.
What we built:
• Natural-language querying that turns plain-English questions into governed dashboards in under 60 seconds
• Federated queries across SQL and NoSQL sources through Trino
• AI query generation on AWS Bedrock Agents, with Bedrock Guardrails keeping model output in bounds
• Dashboards generated with Apache Superset, plus proactive anomaly and trend alerts
• A white-label React widget that embeds in any product
• Role-based access, row-level security and enterprise SSO enforced at every layer
The result:
Zero data egress. The whole platform deploys inside the customer's VPC and is live on AWS Marketplace.
Building AI features for a data-heavy or regulated product? Let's talk about doing it without your data leaving your cloud.
Yup, it is..
It was around 1.4 Seconds and with 3+ tools calling it was around 3 seconds (Staging environment). Much lower in production.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
This is such a great example of turning complex data into a visual experience. 🎾🔥
Love how the court becomes part of the analytics instead of just sitting in the background. Really impressive work!
When does a sports dashboard need the court to be more than a background?
In this case, we were designing Deuce a tennis analytics platform that needed to make complex match data feel immediate and spatial, not just numerical.
The brief was clear: analysts and coaches don't just...
Most outreach tools make you choose: pay per contact, or send from shared servers and hope you don't land in spam.
So I built Knoock.
Upload a CSV/Excel contact sheet → personalize every email + SMS → send through YOUR own senders → track results in real time.
Why own senders matter: your domain, your reputation, your data. No shared-IP spam risk, no per-contact pricing.
Stack: Next.js + Node.js
Live: knoock.devifyo.cloud
If your team still copy-pastes outreach from a spreadsheet, or you need a custom campaign tool, CRM or SaaS MVP built, DM me. Taking on 1-2 new builds this month.
Quick question for founders: what's harder to fix?
A) Low open rates
B) Low reply rates
Drop A or B 👇
The product promise is direct and easy to understand.
GPU infrastructure gets expensive fast, especially when teams are running multiple models, clusters, and workloads at the same time.
Corebit explores a SaaS dashboard experience built to make GPU cost monitoring easier to understand and act on.
The dashboard surfaces compute spend, idle GPUs, workload utilization, potential savings, and optimization opportunities in one clear workspace, helping teams see where capacity is being wasted and what they can improve next.
