FinTech · Trading analytics

AI research agent for an options analytics platform

A subscription analytics platform with 130+ live pages for options flow, dark pool and volatility data, plus an AI research agent on Claude via AWS Bedrock.

live analytics pages
130+
WebSocket routes
100+
agent tools
16
agent versions shipped
8
Context

The challenge

Client
Options analytics company (name withheld under NDA)
Industry
FinTech · Trading analytics

Traders needed answers about live options flow faster than they could click through dashboards, and the business needed an AI feature it could trust with numbers and afford at scale.

Solution

What we built

  1. Core engineering on a four-tier subscription platform with 130+ analytics pages updated live over 100+ WebSocket routes.

  2. AI research agent taken through eight versions, from semantic routing to multi-agent to a single deep agent on Claude via AWS Bedrock, with 16 tools and Postgres-backed conversation state.

  3. Guardrails: server-side tool argument limits, prompt-leak detection, automatic context summarization and a deterministic scoring engine so the model never calculates figures itself.

  4. Per-request LLM cost metering with price snapshots, prompt caching, a page-level chart analysis assistant and Stripe subscription billing.

Architecture

How the system fits together

The path a request or message takes through the production system, end to end.

  1. Browser
  2. WebSocket gateway
  3. Deep agent · Claude on Bedrock
  4. 16 tools
  5. Postgres state
  6. LangFuse traces

Tech stack

  • Django
  • DRF
  • Django Channels
  • Celery
  • PostgreSQL
  • Redis
  • AWS Bedrock
  • LangGraph
  • DeepAgents
  • LangFuse
  • Stripe
Start a project

Have a similar system to build?

Tell us what you want to ship. You will get a technical roadmap and a fixed-scope proposal within 48 hours.

  • Reply within 1 business day
  • NDA on request
  • You own 100% of the IP