# Anubhav

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [Anubhav Sharma](https://cerebralvalley.ai/u/Anubhav_2905)
- **GitHub:** https://github.com/anubhavbuildz/recon-ai.git
- **Demo video:** https://youtu.be/3rwVmSZMoQ8
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1608

Recon AI — AI-Powered Cloud Infrastructure Intelligence

Recon AI is an AI-powered cloud infrastructure assistant built to help developers and engineering teams make smarter infrastructure decisions.

Managing AWS infrastructure requires understanding resource configurations, identifying inefficiencies, and evaluating optimization opportunities. Recon AI simplifies this process through a conversational interface that transforms infrastructure data into actionable insights.

How It Works:
- AWS Lambda and boto3 collect infrastructure information.
- Infrastructure snapshots are stored in Amazon S3.
- Recon AI analyzes the collected data using AI.
- Users can ask natural-language questions about their infrastructure.
- The system identifies potential optimization opportunities and provides evidence-aware recommendations.

Key Features:
- Conversational AWS infrastructure analysis.
- Resource utilization and optimization insights.
- Contextual, actionable recommendations.
- Transparent handling of missing evidence.
- Read-only infrastructure analysis without automatic modifications.

Current MVP Limitations:
- Supports one AWS region.
- Uses a single S3 bucket for infrastructure snapshots.
- AI evaluation is required to validate recommendation accuracy and reliability.
- Historical performance analysis is limited.

Technology Stack:Python, React, AWS Lambda, Amazon S3, boto3, and AI.

Recon AI aims to make cloud infrastructure analysis more accessible, understandable, and actionable while keeping engineers in control of infrastructure decisions.

## More from Meta Global AI Developer Hackathon

- [Behtafood](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1605)
- [Proof Atelier](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1606)
- [aadhaa](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1607)
- [FEN meta synthesis](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1609)
- [Noticer](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1610)
- [Fynex Copilot:](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1611)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1608. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt