Skip to content

A comprehensive learning repository for engineers at all levels to navigate the AI landscape. From foundational concepts to production-ready implementations, this resource guides you through AI/ML fundamentals, Large Language Models, prompt engineering, and modern GenAI tools.

License

Notifications You must be signed in to change notification settings

satinath-nit/ai-compass

Repository files navigation

AI Compass

A comprehensive learning repository for engineers at all levels to navigate the AI landscape. From foundational concepts to production-ready implementations, this resource guides you through AI/ML fundamentals, Large Language Models, prompt engineering, and modern GenAI tools.

Who Is This For?

This repository serves engineers across the experience spectrum:

New Graduates will find structured learning paths that build from mathematical foundations through practical AI applications, with hands-on projects to develop portfolio-worthy skills.

Mid-Level Engineers transitioning to AI will discover how to leverage their existing software engineering expertise while filling knowledge gaps in ML/LLM concepts and tooling.

Senior Engineers can dive directly into production considerations, MLOps practices, and advanced topics like agent architectures and responsible AI governance.

Repository Structure

Start Here (Complete Beginners)

Directory Description
ai-fundamentals/ What is AI, history, how models work, training explained, predictive vs generative AI

Core Learning

Directory Description
foundations/ Mathematical prerequisites, ML basics, deep learning, and LLM fundamentals
learning-paths/ Structured tracks organized by experience level and role
prompt-engineering/ Techniques, patterns, and best practices for effective prompting
llm-systems/ RAG, retrieval, agents, tools, and multimodal systems

Tools and Platforms

Directory Description
genai-tools/ Guides for GitHub Copilot, Windsurf, Claude AI, Gemini, and ChatGPT
agents/ Agent architectures, customization, and implementation patterns

Production and Practice

Directory Description
practical-skills/ Building, debugging, evaluating, and operating AI features
production-ml-llm/ MLOps, deployment patterns, monitoring, and governance
best-practices/ Evaluation strategies, security, UX design, and reproducibility

Career and Ethics

Directory Description
career-and-self-development/ Career paths, interview prep, portfolios, and growth strategies
ethics-and-responsible-ai/ Fairness, safety, privacy, and organizational guidelines

Resources

Directory Description
resources/ Curated external links, reading lists, and reference materials
projects-and-templates/ Starter projects and documentation templates

Quick Start by Experience Level

Complete Beginner (No AI Knowledge)

  1. Start with ai-fundamentals/what-is-ai.md to understand what AI is
  2. Learn the vocabulary in ai-fundamentals/key-terminology.md
  3. Understand ai-fundamentals/how-models-work.md with visual diagrams
  4. Learn ai-fundamentals/training-models.md to see how AI learns
  5. Compare approaches in ai-fundamentals/predictive-vs-generative.md
  6. Then continue to the New Graduate track below

New Graduate (4-8 Week Track)

  1. Start with foundations/math-for-ml.md for mathematical prerequisites
  2. Progress through foundations/ml-fundamentals.md
  3. Learn LLM basics in foundations/llm-fundamentals.md
  4. Practice with prompt-engineering/fundamentals.md
  5. Build your first project using projects-and-templates/
  6. Set up your tools with genai-tools/

Backend Engineer New to AI (2-4 Week Track)

  1. Review foundations/ml-fundamentals.md for core concepts
  2. Deep dive into foundations/llm-fundamentals.md
  3. Master prompt-engineering/ techniques
  4. Learn deployment patterns in production-ml-llm/deployment-patterns.md
  5. Understand llm-systems/rag-and-retrieval.md

Experienced ML Engineer: LLMs and Agents (1-2 Week Track)

  1. Start with llm-systems/ for advanced LLM concepts
  2. Explore agents/ for agent architectures
  3. Review production-ml-llm/ for deployment strategies
  4. Study best-practices/evaluation-for-llms.md
  5. Implement security measures from best-practices/security-for-ai-apps.md

How to Use This Repository

For Self-Paced Learning: Follow the learning paths appropriate to your level. Each section includes explanations, examples, and "Try This" exercises.

As a Reference: Use the table of contents and search functionality to find specific topics when you need them.

For Team Onboarding: Share relevant learning paths with new team members. The structured approach helps standardize AI knowledge across teams.

For Project Planning: Reference the best practices, templates, and checklists when starting new AI features.

Contributing

This is a living document. As AI evolves rapidly, contributions to keep content current are welcome! See CONTRIBUTING.md for detailed guidelines.

Quick contribution ideas:

  • Fix errors or outdated information
  • Add new examples or exercises
  • Improve explanations
  • Add coverage of new topics
  • Translate content

License

This project is licensed under the MIT License - see the LICENSE file for details.

This means you are free to use, modify, and distribute this content for any purpose, including commercial use.


Navigate the AI landscape with confidence. Start your journey today.

About

A comprehensive learning repository for engineers at all levels to navigate the AI landscape. From foundational concepts to production-ready implementations, this resource guides you through AI/ML fundamentals, Large Language Models, prompt engineering, and modern GenAI tools.

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published