Case study · Web app

SessionPulse: live market data with an AI sentiment layer on top

Trading-session intelligence for traders — real-time data pipelines, an AI reading of market sentiment, and an interface built for glancing, not studying.

SessionPulse — interface screenshot

The brief

Traders do not need another dashboard with forty widgets. They need to know what the current session looks like in five seconds, and what the mood behind it is. SessionPulse had to compress live data into something readable at a glance, at 6am, on a phone.

What we built

A Next.js web app with scheduled server-side data pulls, cached aggregation and a dark, high-contrast interface designed around a single amber accent so that the numbers carry the attention rather than the chrome.

The AI layer summarises sentiment from market inputs into a short, plain-language read that sits beside the raw data instead of replacing it — the trader still sees the numbers that produced the opinion.

  • Next.js app with server-side scheduled data ingestion
  • Postgres storage with cached aggregation for fast page loads
  • AI sentiment summarisation layered over live inputs
  • Session-aware dark interface, mobile first
  • Accounts, subscription tiers and access control
  • Packaged mobile builds submitted to the app stores

Stack

  • Next.js
  • TypeScript
  • Supabase
  • Postgres
  • Vercel
  • AI APIs
Proof of work

Shipped, not mocked up

All selected work →

Want this level of build for your product?

One message with what you are making. You get a fixed scope and a fixed price.

Free 20-minute call · fixed written quote · no discovery fee
Keep reading