AI/ML Foundations and Agentic AI Architecture

This repository documents my structured progression toward becoming an Agentic AI Solutions Architect (AWS-native).

It combines foundational AI/ML understanding with enterprise-oriented agentic system design.

Strategic Focus

This repository is intentionally aligned with:

• Agentic AI systems on AWS
• Amazon Bedrock Agents
• AgentCore and Strands Agents
• Retrieval-Augmented Generation (RAG)
• Model Context Protocol (MCP)
• Enterprise architectural tradeoffs

The objective is not to collect notes.

The objective is to design, implement, and document production-aware Agentic AI architectures.

---

Architectural Philosophy

Every implementation in this repository considers:

• Training vs Inference boundaries
• IAM isolation and security posture
• Memory persistence strategy
• Observability and monitoring
• Failure modes and mitigation
• Cost and latency modeling
• Scalability patterns

This repository evolves alongside hands-on coursework and architectural exploration.

---

Repository Structure

ai-ml-foundation-and-applied-systems/
├── architectures/
│   └── adr/             # Architecture Decision Records
├── course_notes/
│   ├── prereqs/         # Prerequisite topics and background material
│   └── weekly/          # Weekly course notes and summaries
├── hands_on/            # Practical experiments, notebooks, and projects
├── docs/                # Additional documentation and references
└── README.md

Overview

This repository serves as a centralized workspace for:

• Course Notes — Organized notes from weekly sessions and prerequisite material
• Architecture Decisions — Records of key design and architectural choices (ADRs)
• Hands-On Work — Experiments, implementations, and applied projects
• Documentation — Supporting docs, references, and guides

Architectural Decision Records (ADRs)

Key design decisions are documented under:

architectures/adr/

Each ADR captures:

• Context
• Decision
• Tradeoffs
• Consequences
• Risk mitigation

This ensures architectural clarity and enterprise readiness.

Getting Started

Clone the repository:

git clone https://github.com/tvprasad/ai-ml-foundation-and-applied-systems.git
cd ai-ml-foundation-and-applied-systems

Long-Term Objective

By the end of this progression, this repository will contain:

• A reference Agentic AI architecture on AWS
• Enterprise-ready system diagrams
• A documented AI Solutions Architect playbook
• Hands-on implementations aligned with architectural decisions

This is an evolving architecture body of work.