Financial Advisor

Inspiration

What it does

How we built it

Challenges we ran into

Accomplishments that we're proud of

What we learned

What's next for Financial Advisor

Inspiration

Managing personal finances is hard — people often lose track of daily expenses and overshoot budgets. We wanted to create an AI-powered assistant that helps users stay financially healthy in real time.

What it does

Financial Advisor (Budget Guardian) classifies your messages as transactions, goals, queries, or budget checks using Amazon Bedrock. It then routes them to the right AI module and can even suggest top 5 investment options based on current market factors. The system interacts via Telegram for simplicity.

How we built it

We used AWS Lambda, Amazon Bedrock, and Telegram Bot API. Bedrock handles natural language understanding and investment insights, while Lambda functions handle intent routing, transaction logging, and budget monitoring.

Challenges we ran into

Tuning Bedrock prompts for accurate intent classification.

Normalizing responses from multiple child Lambda functions.

Handling conversational context within a stateless architecture.

Accomplishments that we're proud of

Built a fully serverless financial AI assistant.

Integrated Bedrock’s LLM for real-time classification and smart insights.

Created an intuitive Telegram interface for seamless user interaction.

What we learned

How to integrate Bedrock LLMs into event-driven architectures.

The importance of response normalization in multi-function systems.

Balancing simplicity with smart automation in conversational design.

What's next for Financial Advisor

Add personalized financial analytics dashboards.

Introduce voice-based interaction and multilingual support.

Extend investment recommendations with live market APIs.

Built With

• amazon-rds-relational-database-service
• amazon-sns
• aws-api-gateway
• bedrock
• lambda
• nova
• postgresql
• python
• sagemaker
• telegram