LLM tools · Product experiment
AI Portfolio Rebalancer
A LangChain agent that selects financial tools, identifies portfolio imbalances, considers market context, and compares model behavior across providers.
The challenge
Start with the product question.
Portfolio analysis combines deterministic calculations with narrative interpretation. The product question is where an LLM adds value—and where a dedicated tool should stay in control.
What I built
A working system to learn from.
I created tools for price lookup, equal-weight rebalancing, and market-trend analysis, then connected them through LangChain agents using OpenAI and Groq models. The experiment also captures differences in speed, accuracy, and tool use.
Product decisions
The thinking behind the build.
- 01
Keep calculations inside deterministic tools and use the model for orchestration and explanation.
- 02
Compare providers on behavior that matters to the workflow, not only answer style.
- 03
Make tool selection visible enough to inspect and improve.
- 04
Frame generated guidance as an experiment rather than professional financial advice.
This is an independent project shared to demonstrate product thinking and hands-on exploration. It does not represent confidential employer work or commercial performance claims.