01 / AI-first

2026 · Confidential · Live

Equity Research RAG Platform

Enterprise RAG for stock and market research, cited, time-aware answers over SEC filings, news, earnings transcripts, and a user's own notes.

Confidential

FintechRAGResearchNDA
  • 01

    Automated filings plus manual/BYO documents

  • 02

    Per-ticker vector collections with rerank

  • 03

    LLM-as-judge eval harness

  • 04

    Production access control from day one

The brief

Equity research means reading through dense SEC filings, news, and transcripts, then citing the right source when you make a claim. Off-the-shelf chat tools answer confidently but don't reliably ground claims in the actual filing text, and don't handle a user's own private notes and documents alongside public filings in the same place.

The outcome

  1. 01Dual ingest modes (automated filings + manual/BYO documents) into one unified per-ticker knowledge base
  2. 02Built-in LLM-as-judge evaluation harness to score answer quality against a held-out eval set
  3. 03Query rate-limited and session-authenticated, with a separate admin-key-gated ingestion and eval surface, production access control from the start

The build

A dual-ingestion RAG pipeline: one path automatically pulls SEC 10-K/10-Q filings, news, and transcripts per ticker; a second lets a user paste notes, a URL, or upload a PDF. Both land in the same per-ticker vector store so a query can draw on public filings and private research together.

Every answer is cited back to source. PDF uploads are processed for text and then discarded, not retained, keeping the ingestion path lightweight and auditable.

Specs

Platform
Web, chat interface with All/Uploads/Filings corpus filter
Ingestion
Automated (SEC filings, news, transcripts) + manual (notes, URL, PDF upload)
Retrieval
Per-ticker vector collection, reranked before answer generation
Eval
LLM-as-judge harness against a held-out query set

Stack

AI / ML
Anthropic ClaudeVoyage embeddingsCohere rerank
Backend
GoRiver workers
Frontend
Next.js
Data
PostgreSQLRedisQdrant

Building something in this layer?

Start an inquiry

More AI-first

All AI-first