Agentic AI · Workflow orchestration
Multi-Agent Investment Advisor
A multi-agent system that transforms a natural-language goal into a structured investment strategy through specialized analysis and coordinated decision-making.
The challenge
Start with the product question.
Financial goals arrive as ambiguous human language, while useful guidance requires structured goals, current context, risk reasoning, and a coherent recommendation.
What I built
A working system to learn from.
I designed a sequence of specialized agents for goal extraction, market context, retrieval, investment and risk review, consensus, presentation, and feedback. A FastAPI backend connects the orchestration to a React experience.
Product decisions
The thinking behind the build.
- 01
Assign narrow responsibilities to agents instead of relying on one oversized prompt.
- 02
Use a coordinating step to resolve competing specialist recommendations.
- 03
Keep the experience legible by presenting one coherent strategy to the user.
- 04
Design feedback as an input to refinement, not as a dead-end rating.
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.