Projects

A technical hub for production-ready AI engineering projects. Learn best practices for building, deploying, and scaling AI systems in real-world production environments.

📬Subscribe on Substack YouTube Channel GitHub

AI Agents

2026-05

15 min

F1 AI Race Engineer: AI-Powered Race Replay and Strategy Insights

Interactive F1 dashboard with race replay, telemetry, strategy, and AI-generated insights powered by FastF1 and modern LLM tooling.

FastF1FastAPINext.jsLLM

F1 AI Race Engineer is a full-stack AI racing analytics project that combines FastF1 data with an interactive dashboard and AI reasoning workflows. It lets users replay completed race weekends and inspect standings, tyre strategy, position changes, weather evolution, and race control events in a single interface. The platform includes race overview, race replay, telemetry comparison, and AI-generated race summary and driver insights features. It is designed as a production-style system with FastAPI backend services, a modern frontend, and configurable LLM integrations.

FastF1FastAPINext.jsTelemetryAI AgentsLLMMotorsport AnalyticsDocker

View on GitHub Watch Demo

RAG

2025-01

25 min

SentiWiki AI: End-to-End Agentic RAG for ESA Copernicus Sentinel Missions

Production-grade agentic RAG system deployed on AWS ECS for querying ESA Copernicus Sentinel mission documentation with 96.1% faithfulness.

LangGraphQdrantFastAPIAWS ECSNext.jsDocker

SentiWiki AI is an end-to-end agentic RAG system that treats documentation retrieval as an intelligent engineering problem. It distinguishes between looking up a fact (Retrieval) and deriving an answer (Reasoning), using LangGraph-based agents to route queries, decompose complex questions, and retrieve grounded answers from 66+ SentiWiki documents. The system is built as a production-grade, fully deployed stack on AWS ECS Fargate, demonstrating real-world engineering practices including end-to-end data pipelines, agentic intelligence, hybrid retrieval, asynchronous FastAPI backend, and complete observability.

LangGraphQdrantFastAPILiteLLMNext.jsRAGASAWS ECSPrometheusGrafanaClaude 3Crawl4AIDockerRAGProduction SystemsSentinel Missions

View on GitHub 📬Read on Substack

Learning Path (SentiWiki AI Series)

View All on Substack

Building an end-to-end agentic RAG deployed on AWS for ESA SentiWiki (Part 1): Project Overview

25 min

Welcome to Ad Astra AI — a technical hub where I'll be building production-ready AI engineering projects. This is the entry point to a full series that explains every part of the SentiWiki AI system, from data scraping to AWS deployment.

📬Read on Substack

Building an end-to-end agentic RAG deployed on AWS for ESA SentiWiki (Part 2): Data Scraping with Crawl4AI

20 min

How SentiWiki is scraped, cleaned, and turned into markdown ready to be ingested. Learn about Crawl4AI, Breadth-First Search strategies, and cleaning pipelines for RAG-ready data.

📬Read on Substack

Building an end-to-end agentic RAG deployed on AWS for ESA SentiWiki (Part 3): Chunking & Ingestion

18 min

Sentiwiki structure-aware chunking, metadata, and local embeddings, and ingestion.

📬Read on Substack

Building an end-to-end agentic RAG deployed on AWS for ESA SentiWiki (Part 4): Advanced Retrieval Pipeline

Hybrid search (semantic + keyword), Qdrant, reranking, and retrieval strategies.

📬Read on Substack

Building an end-to-end agentic RAG deployed on AWS for ESA SentiWiki (Part 5): Agentic RAG with LangGraph

LangGraph agents for routing, query rewriting, grading, and multi-step flows.

📬Read on Substack

Building an end-to-end agentic RAG deployed on AWS for ESA SentiWiki (Part 6): Evaluation & Monitoring with RAGAS, adversarial test, Prometheus/Grafana and LangSmith

RAGAS evaluation, adversarial test sets, metrics, Prometheus/Grafana dashboards, and LangSmith traces.

📬Read on Substack

Building an end-to-end agentic RAG deployed on AWS for ESA SentiWiki (Part 7): Backend with FastAPI & Frontend with Next.JS

FastAPI API design, real streaming, Dockerization, and the Next.js chat UI.

📬Read on Substack

Building an end-to-end agentic RAG deployed on AWS for ESA SentiWiki (Part 8): Docker Compose & CI/CD with GitHub Actions

Docker Compose setup and automated CI/CD pipelines with GitHub Actions.

📬Read on Substack

Building an end-to-end agentic RAG deployed on AWS for ESA SentiWiki (Part 9): AWS Deployment with ECS/Fargate architecture, ALB, Secrets Manager, and S3

ECS/Fargate architecture, Application Load Balancer, Secrets Manager, Cloud Map, scaling and costs.

📬Read on Substack