_##Inspiration
We noticed that startup data is available online, but it is not easy to understand. Many students and beginners do not know how to analyze this data properly. We wanted to build a platform that makes unicorn startup data simple, structured, and useful for decision-making.
What it does
AUSIP analyzes unicorn startup data and gives clear insights. Users can ask questions in normal language instead of writing technical queries. The system studies the data, compares industries, and provides structured results with explanations. It helps users understand trends, growth, and investment opportunities.
How we built it
We used Elasticsearch to store and analyze large amounts of startup data quickly. We used Elastic AI Agents to automatically select the right tools and generate structured answers. The backend was built using FastAPI to handle requests smoothly. The frontend was built using React, TypeScript, and Tailwind CSS to create a clean and easy-to-use interface.
Challenges we ran into
One challenge was designing the data structure correctly so that the analysis would be accurate. Another challenge was connecting the AI agent with Elasticsearch tools in a proper way. We also worked hard to make sure the results were clear and not confusing.
Accomplishments that we're proud of
We successfully built an autonomous system that can analyze startup data without manual queries. We created a clean and professional interface. We made sure every answer is structured and based only on real data, not assumptions.
What we learned
We learned how powerful Elasticsearch can be for real-time analytics. We understood how AI agents can automate tool selection and reasoning. We also learned the importance of clean data design and clear output formatting.
What's next for AUSIP - AI Unicorn Strategy Intelligent Platform
In the future, we plan to add real-time data updates and advanced visualization features like charts and dashboards. We also want to improve the scoring model to make investment insights even more accurate and helpful._
Built With
- aes
- amazon-web-services
- bcrypt
- bedrock
- chartjs
- claude
- cpython
- elasticsearch
- esql
- fastapi
- html
- httpx
- jwt
- kibana
- orchestrator
- orm
- passlib
- pydantic
- python
- python-jose
- react
- reportlab
- sqlalchemy
- tailwindcss
- typescript
- uvicorn
- vectordb
- vite
Log in or sign up for Devpost to join the conversation.