Show HN: I built an AI agent that helps me invest
Hacker News - AI
Jul 19, 2025 13:46
haniehz
1 views
hackernewsaidiscussion
Summary
A developer built a modular AI agent system, "mcp-agent," to assist with complex investment decisions, including stocks and real estate, by pulling live data, personalizing recommendations, and improving over time. Unlike general chatbots, this system uses multiple specialized agents, persistent memory, and human-in-the-loop features for higher-quality, tailored results. This highlights the potential of customizable, domain-specific AI agents to handle nuanced, multi-variable decision-making tasks beyond generic AI models.
A while back, I built a simple app to track stocks. It pulled market data and generated daily reports based on my risk tolerance. Basically a personal investment assistant. It worked well enough that I kept going. Now, the same framework helps me with real estate: comparing neighborhoods, checking flood risk, weather patterns, school zones, old vs. new builds, etc. It’s a messy, multi-variable decision—which turns out to be a great use case for AI agents. Instead of ChatGPT or Grok 4, I use mcp-agent, which lets me build a persistent, multi-agent system that pulls live data, remembers my preferences, and improves over time. Key pieces: • Orchestrator: picks the right agent or tool for the job • EvaluatorOptimizer: rates and refines the results until they’re high quality • Elicitation: adds a human-in-the-loop when needed • MCP server: exposes everything via API so I can use it in Streamlit, CLI, or anywhere • Memory: stores preferences and outcomes for personalization It’s modular, mod