ArthVest — Your AI Investment Research Desk

The description states that ArthVest is an AI research tool designed to automate parts of investment analysis. It uses LangGraph workflows with specialized agents to:

• Discover opportunities using economic, market, and news context.
• Analyze fundamentals, technical indicators, sentiment, and chart patterns.
• Compare independent bull and bear arguments.
• Validate confidence, risk, and contradictory evidence.
• Produce a BUY, SELL, or WAIT verdict.
• Save complete evidence-backed reports.

It is built with React/TypeScript on the frontend and FastAPI/PostgreSQL/Supabase on the backend. It uses OpenAI models (GPT-5.6 Terra, Sol) and Codex for development.

Inference The product appears to be a structured AI research assistant that aims to reduce time spent collecting data and increase consistency in analysis by using agent-based workflows.

The author positions ArthVest as an AI investment research desk that transforms fragmented research into a structured, explainable workflow. It is described as helping analysts complete complex research faster and more consistently, reducing reliance on disconnected tools.

It claims to support the Work & Productivity category, emphasizing automation of evidence collection and preservation of each analysis as a reusable work product.

Inference The positioning suggests ArthVest targets investment professionals or analysts who want to streamline their research process. However, it is not clear if this is a niche within finance or a broader B2B SaaS offering.

The description does not identify specific customer segments or personas. It implies that the target user is someone involved in investment research — such as analysts, portfolio managers, or financial researchers — who needs structured, evidence-backed reports.

Inference Based on the product’s focus on analyzing investments and generating research reports, it likely targets professionals working in finance or investment management. However, no explicit customer data or segmentation is provided.

There is no evidence of a business model or pricing structure. The description states that ArthVest supports research and education but does not execute trades or provide personalized financial advice. It also notes that every output should be independently reviewed.

Inference The product appears to be non-commercial in nature, possibly intended for demonstration or educational use only. No indication of monetization strategy exists.

ArthVest is built using:

• Frontend: React + TypeScript
• Backend: FastAPI, LangGraph, OpenAI models (GPT-5.6 Terra/Sol), PostgreSQL/Supabase
• Development tools: Codex for architecting, implementing, testing, and documenting the system

It uses two LangGraph workflows:

1. Discovery workflow covering economic → market pulse → news → macro context → planner → discovery.
2. Analysis workflow involving context → planner → parallel specialists → merge → horizon check → debate → decision → validation.

Agents are designed to independently analyze technical, fundamental, sentiment, and chart evidence before combining findings.

Inference The architecture shows a sophisticated use of AI agents for structured reasoning and task delegation. The use of Codex suggests an iterative development approach with strong prompt engineering and system design.

There is no evidence of traction or adoption beyond the hackathon submission. The project was built in seven days by one person (Rushil Mehta). No revenue, customers, or usage metrics are mentioned.

Inference The product remains at a prototype stage and has not demonstrated real-world utility or scalability. It lacks any indication of market validation or user feedback.

No competitive landscape is described. The author does not mention existing tools or platforms in the investment research space, nor does it compare ArthVest to them.

Inference Without a reference point, it's unclear how ArthVest fits into the current market for AI-powered financial research or analysis tools. It may be competing with traditional research platforms or newer AI-based solutions, but this is not stated.

• Single-person development: The entire project was built by one individual in a short timeframe.
• No commercial traction: No evidence of users, revenue, or product-market fit beyond the hackathon.
• Unverified claims: All features and capabilities are self-reported without external validation.
• Unclear scalability: The architecture is not shown to be scalable beyond a prototype.
• Limited domain expertise: The author’s background in finance or investment research is not stated.

1. What specific problems in investment research does ArthVest solve, and how do you know?
2. Have you tested the system with actual investment professionals or analysts?
3. How would you scale this from a single-person hackathon project to a commercial product?
4. Is there any plan for monetization or revenue generation?
5. What are the limitations of using GPT-5.6 Terra/Sol in this context, and how do you handle model hallucinations or biases?