08Engineering Decisions

Why I built it this way.

Every technology choice solved a real engineering problem. Nothing was selected because it was fashionable.

D01
Optimize for Iteration
TanStack Start

Chosen for fast builds, server functions, and a simple architecture so product iteration stays fast without framework lock-in.

D02
Latency Before Infrastructure
Cloudflare Workers

Global execution and extremely low cold-start latency fit real-time market intelligence better than traditional serverless deployments.

D03
Build the Product, Not the Plumbing
Supabase

Realtime database, authentication, scheduling, security, and storage let development focus on trading intelligence instead of infrastructure.

D04
One AI Gateway, Many Models
Lovable AI Gateway

A single AI integration layer provides model flexibility, consistent behavior, centralized governance, and cost visibility across every agent.

D05
Reliable Data Over Easy Data
Firecrawl

When financial websites don't expose APIs, reliable structured extraction becomes more valuable than fragile scraping pipelines.

D06
Concurrency Without Complexity
Postgres

The database became the synchronization layer using transactions, locking, idempotency, and conflict handling instead of introducing additional infrastructure.

Architectural Decision

Why a multi-agent architecture?

The easiest path would have been to hand every question to a single large model and trust the output. It would have shipped faster. It would also have been impossible to defend when things went wrong.

Instead, EdgeQuant separates intelligence into specialised systems. Different agents own different responsibilities: market analysis, prediction, risk, portfolio construction, governance, learning, deployment, and validation. Each has a narrow mandate, a clear input contract, and an output that another agent is allowed to challenge.

That separation is not academic. It produces higher explainability because every decision can be attributed to the agents that shaped it. It produces better governance because no single model is trusted to be right about everything. It makes validation tractable, because a narrow agent can be tested against a narrow expectation rather than a vague notion of "good."

It also produces stronger reliability. When one agent degrades, its scope of damage is bounded and the surrounding system notices. And it produces continuous improvement, because each agent can be measured, retrained, and replaced on its own without rebuilding the platform around it.

One model that does everything is a black box. A committee of specialists is a system you can actually operate.