The version of your product I wish I had

Build your own AI stock research tool! This talk covers creating an AI layer over existing content, automating alerts, and a Next.js frontend with chat and portfolio analysis.

Claude Sonnet 4 Vercel AI Gateway AI SDK v6 Next Robinhood Agentic Trading MCP

Overview

I pay for a stock-research subscription and wanted a better version of it than the website they provide, so I built my own AI layer and front end over their content. Python crons on GitHub Actions poll trade alerts, distill newly published articles, and send me a weekly digest. The frontend is a Next.js app with a chat agent and gap analysis tool that compares my investment account holdings against the fund’s current portfolio using Robinhood’s Agentic Trading MCP server.

Links

https://github.com/hunterphillips/iofund-iq
TypeScript/Python Next.js app querying Neon Postgres via Sonnet 4.6.
https://iofund-iq.vercel.app
AI-powered financial subscription query interface analyzing portfolio sector allocations.

Tech stack

Claude Sonnet 4

Anthropic's mid-tier model: balances state-of-the-art coding (72.7% on SWE-bench) with cost-efficiency for high-volume, agentic workflows.

Claude Sonnet 4, released May 22, 2025, is Anthropic's versatile, mid-tier model (successor to Sonnet 3.7). It delivers superior coding performance, achieving a state-of-the-art 72.7% on SWE-bench. The model features hybrid reasoning: it offers both near-instant responses and an 'extended thinking' mode for deeper analysis. Optimized for high-volume applications, Sonnet 4 provides an optimal balance of capability and practicality, with pricing set at $3/$15 per million tokens (input/output). Access is readily available via the Anthropic API, Amazon Bedrock, and Google Cloud's Vertex AI.

https://www.anthropic.com/claude

View projects
Vercel AI Gateway

Unify access to 100+ LLMs (OpenAI, Anthropic, etc.) via a single, robust API endpoint, centralizing routing, failover, and observability.

The Vercel AI Gateway provides a unified API endpoint for accessing over 100 large language models (LLMs), including top providers like OpenAI and Anthropic. This centralized interface eliminates the overhead of managing multiple API keys and provider accounts, streamlining your production AI workloads. Key features include intelligent failover for increased uptime, built-in observability for detailed usage and cost tracking, and automatic prompt caching. Utilize the Bring Your Own Key (BYOK) option for a 0% markup on token pricing, ensuring cost-efficiency and maximum throughput.

https://vercel.com/docs/ai-gateway

View projects
AI SDK v6

Vercel AI SDK v6 is a production-ready TypeScript toolkit that simplifies building multi-model AI applications with native agent abstractions and human-in-the-loop tool approvals.

Vercel AI SDK v6 streamlines the development of complex AI applications by offering a unified, provider-agnostic interface for models like OpenAI and Anthropic. This major release introduces dedicated agent abstractions to decouple declaration from usage, built-in human-in-the-loop tool execution approvals for safer function calling, and full Model Context Protocol (MCP) support. By combining robust streaming utilities with structured JSON outputs and interactive UI hooks, the toolkit helps you ship secure, multi-step agentic workflows directly inside React, Next.js, and other modern frameworks.

https://sdk.vercel.ai/docs

View projects
Next

Next.js is the full-stack React framework: it delivers high-performance web applications via hybrid rendering and powerful, Rust-based tooling.

This is the React Framework for production: Next.js enables you to build full-stack web applications with zero configuration and maximum efficiency. It supports a hybrid rendering approach (Server-Side Rendering, Static Site Generation, and Incremental Static Regeneration) for optimal speed and SEO performance. Key features include React Server Components, Server Actions for running server code directly, and the App Router for advanced routing and nested layouts. Developed by Vercel, it leverages Rust-based tools like Turbopack and the Speedy Web Compiler for the fastest possible builds and a superior developer experience.

https://nextjs.org/

View projects
Robinhood Agentic Trading MCP

Robinhood Agentic Trading MCP connects third-party AI agents directly to a dedicated Robinhood account to research markets, rebalance portfolios, and execute trades using natural language.

Robinhood Agentic Trading utilizes the Model Context Protocol (MCP) to bridge the gap between LLMs and active brokerage accounts. By adding a single URL to an MCP configuration, users can link developer-centric AI agents (such as Claude Code) to a dedicated, isolated Robinhood account. This integration allows the agent to safely check balances, analyze market data, and execute equity orders based on natural language prompts. Built-in safety guardrails ensure the AI operates within a user-defined budget, providing real-time trade notifications and instant disconnect options directly inside the Robinhood app.

https://robinhood.com/us/en/support/articles/agentic-trading-overview/

View projects

The version of your product I wish I had

Related talks