Multi-Agent Investment Research Platform for BRDGE Insights

An AI-powered investment research platform, Strēm turns a fragmented, data-heavy investment research process into one connected workflow.

mvp

The Client

Strēm is a context-aware AI investment research platform for analysts, portfolio managers, and sector researchers. It was founded by Torrence Jennette (investment professional) and Mallory Musante (marketing analytics expert).

The MVP Goal

In Part 1, the team completed a full discovery phase: persona research, feature mapping, system architecture, and a Figma prototype.

Now at this stage we had to bring this prototype to life. We worked in two-week cycles with regular client demos to keep priorities aligned. The MVP had to handle financial data, answer research questions, and be tested by actual users.

Outcome

MVP Development: 3 Key Stages

Building the MVP came down to 3 key stages. Each one was necessary to bring together a platform that combines a multi-agent AI system with an automated data pipeline monitoring 3,000+ US securities daily.

1. Data Infrastructure – we built an automated pipeline connecting four data sources: financials, stock prices, macro indicators, and regulatory filings, covering 3,000+ US companies.

2. AI Agent System – rather than one model doing everything, specialized agents work in parallel: one tracks news, one checks financials, one handles valuations. A lead agent coordinates the team and delivers a single, combined answer.

3. Platform and Core Workflows – one unified workspace replaces fragmented dashboards. Built around a central chat, it includes a company dashboard with filings and news, a cross-company news feed, watchlist and coverage management, and report export to PDF and Excel.

Click to watch the full demo that will guide you through all platform features we developed.

www.brdgeinsights.com

3 Key Features

The first MVP iteration is a working prototype of a multi-agent investment research platform designed to help analysts work faster and access more valuable information. It features a minimalistic design with three prioritized core features. The goal is to test the prototype as soon as possible and improve functionality based on user feedback.

Feature 01

"Research" to quickly find relevant info

At the center of the platform is a natural language interface that acts as a specialized financial assistant. Analysts ask questions in plain English, and the AI pulls from real-time financial data, SEC filings, and news sources to deliver precise, citation-backed answers.

This module directly connects raw data to instant insights, minimizing routine research time.

Feature 02

"Coverage" to add context to your research

This is where Strēm separates itself from generic AI tools. The platform doesn’t just process isolated queries; it acts as a context-aware intelligence system. Analysts can build a Coverage list by tracking specific companies, assigning strategic positions, and adding personal investment notes.

The AI remembers this context, allowing teams to run retrospectives on past predictions and compare positions against market benchmarks. Because this context is shared at the company level, portfolio managers and researchers can seamlessly view their teammates’ insights, transforming the platform into a collective intelligence hub.

In an industry where timing and alignment matter, that shared layer of memory is what turns individual analysis into a competitive advantage.

Feature 03

"Alerts & Monitoring" to keep you in the context

To ensure analysts never miss a critical market movement, an automated news pipeline runs continuously. News appears seamlessly within the active Research chat, inside dedicated company dashboards, and in a standalone feed.

The Alerts system is tied directly to the user’s Coverage list and proactively notifies them only when highly relevant events impact the specific securities they are tracking.

This means analysts spend less time scanning for updates and has more time to analyze them and make educated decisions.

Here you can see all the notifications a user has set to stay up to date. Source: BRDGE Insights, LLC

Challenges & Solutions

Building an AI research platform for financial professionals comes with specific technical challenges. Here's what the team encountered and how it was addressed:

//Before
//After
[1]
QUERY AMBIGUITY
Financial questions are often ambiguous. The same term can mean different things in different contexts.
Solved with query parsing, key term caching, and pre-defined templates per user role.
[2]
TEXT-TO-SQL ACCURACY
Generating accurate database queries from natural language is hard.
Solved with schema-driven prompts, query validation, and a feedback loop to catch incomplete results.
[3]
MODEL RELIABILITY
AI models can produce confident but incorrect answers (hallucinations).
Solved by keeping each agent narrowly scoped, requiring source citations, and monitoring outputs.
[4]
DATA SCALING
Processing data for 3,000+ companies daily at scale.
Solved with an automated pipeline using AWS EventBridge, SQS, and Lambda with retry logic for failed jobs.
[5]
MULTI-AGENT CONTEXT
Agents need to share context mid-query. If one agent finds something relevant, others need to know.
Solved by passing enriched context explicitly between agents through the Orchestrator.

Results

3,000+

US securities monitored with daily automated data collection

80+

features defined across 8 development areas

6

specialized AI agents working in coordination

4

integrated data sources

40%

target reduction in routine analysis time for investment professionals

What stands out most is their ability to combine technical execution with strategic thinking. They have not just built what we asked for. They’ve strengthened the product by asking smart questions, identifying gaps, and making thoughtful recommendations along the way..

Mallory Musante

//Mallory Musante,

CEO, BRDGE Insights

Read full review on Clutch

Let's collaborate

Tell us a bit about your project or challenge, and we'll get back to you shortly.

Volodymyr Hresko Volodymyr Hresko Co-Founder & COO

Reach out directly

[email protected]
This field is for validation purposes and should be left unchanged.
Full name
By submitting the form, you agree to Coxit’s Privacy Policy.