Choose what you want to do next
Each collection starts with a useful entry point. Follow the related guides when your project needs more depth.
Plan your learning
Choose a starting point and move through skills with observable milestones.
Take away: A practical sequence from Python to a reviewed portfolio.
Open the learning roadmapBuild a portfolio
Compare project scopes across retrieval, tools, workflows and service deployment.
Take away: A project brief with deliverables and checks.
Explore project ideasLearn Python application skills
Build the program around the model: inputs, validation, errors and tests.
Take away: A working application boundary.
Read the Python LLM guideAnswer from your documents
Understand source preparation, retrieval choices and supported answers.
Take away: A small RAG implementation plan.
Start with RAGDesign agents and integrations
Decide when a tool-using loop helps and how to keep its responsibilities clear.
Take away: A bounded workflow you can trace.
Explore AI agentsEvaluate and operate
Move beyond a convincing demo with tests, release records and operational signals.
Take away: A repeatable quality-review process.
Build an evaluation plan
Browse by topic
Career planning and foundations
Retrieval, agents and frameworks
Operations and workplace integrations
Read, build, then return with a question
Choose one guide and produce its suggested artifact before opening several more tabs. A small architecture sketch or test sheet reveals the next question more clearly than another list of tools.
The glossary gives short explanations; practical guides add examples and decisions. Course pages describe structured training and should be reviewed separately for prerequisites, delivery and scope.
Three ways through the library
New to application development: begin with Python foundations, then a small LLM application and a portfolio exercise. Already building software: start with the RAG or agent guide and follow the evaluation material.
Reviewing an existing system: use the production architecture and LLMOps guides to inspect source changes, access, failure handling and release quality. Return to a glossary definition only when a term is unclear.
Choose a resource by what you need to learn
Keep the quick topic navigation above for browsing. These descriptions explain what each resource covers and who it is for. Start with the overview and roadmap, build Python/API foundations, then choose retrieval or agents before moving into evaluation and operations.
Beginner · Career
AI Engineering Guide
The definitive overview of AI engineering — what it is, what AI engineers do, the skills required, tools used, career paths, and how the discipline compares to data science and ML engineering.
Beginner · Career
AI Engineering Roadmap
A staged learning path with skills, practice and project milestones. For beginners and developers planning their next step; progress depends on demonstrated work, not a guaranteed job-ready deadline.
Career
AI Engineer Salary India
Career and compensation research guidance by role, seniority and location. Learn how to interpret salary evidence and compare responsibilities without treating a range as an offer or guarantee.
Developer · Career
AI Engineer Skills
Complete technical skill map for AI engineers — Python, prompt engineering, RAG, LangChain, LangGraph, agents, MCP, evaluation, deployment, and observability.
Developer
AI Engineer Projects
Portfolio project ideas with architecture guidance — covering RAG pipelines, document assistants, LangGraph agent workflows, and deployed FastAPI AI services.
Career · Developer
AI Engineering Interview Questions
Complete AI engineering interview preparation guide — LLMs, RAG, vector databases, agents, LangChain, MCP, system design, deployment, project walkthroughs, and a 30-day prep plan.
Beginner · Developer
What is RAG?
Complete explainer on Retrieval-Augmented Generation — how it works, why it is used, the full pipeline from document loading to RAGAS evaluation, and enterprise use cases.
Developer · Advanced
RAG vs Fine-Tuning
Side-by-side comparison of RAG and fine-tuning — best use cases, trade-offs, data requirements, production challenges, and a decision framework for choosing between them.
Beginner · Developer
What is a Vector Database?
Complete guide to vector databases — embeddings, semantic search, vector search mechanics, tools comparison (Pinecone, Chroma, FAISS, pgvector), RAG integration, and best practices.
Developer · Advanced
Production RAG System Architecture
Complete 13-layer production RAG architecture guide — data ingestion, chunking, embeddings, vector databases, retrieval, reranking, prompt orchestration, evaluation, monitoring, security, and deployment.
Beginner · Developer
What Are AI Agents?
Comprehensive guide to AI agents — tools, memory, workflows, multi-agent systems, enterprise examples, and how agentic systems differ from simple LLM applications.
Developer · Career
Agentic AI Explained
Deep explainer on agentic AI — what it means, how agentic workflows are designed, tool use, planning, multi-step reasoning, and real enterprise deployment examples.
Developer · Advanced
LangGraph vs CrewAI
Production comparison of LangGraph and CrewAI — design philosophy, state management, observability, learning curve, and decision guidance for enterprise agent deployments.
Developer
What is LangGraph?
Complete guide to LangGraph — stateful graph-based AI agent workflows, nodes, edges, state management, conditional routing, human-in-the-loop, RAG orchestration, and production agent best practices.
Developer
What is LangChain?
Complete guide to the LangChain framework — key components, how it powers RAG pipelines and AI agents, comparison with building from scratch, limitations, best practices, and skills needed.
Developer · Advanced
What is MCP?
Full explainer on Model Context Protocol (MCP) — the open standard for connecting AI agents to tools, data sources, and APIs. Covers architecture, MCP servers, clients, and enterprise use cases.
Developer
LLM Prompt Engineering Guide
Practical guide to LLM prompt engineering — system prompts, prompt templates, structured outputs, RAG prompts, tool-calling instructions for agents, prompt evaluation, versioning, and production use.
Developer · Advanced
What is LLMOps?
Complete guide to LLMOps — the practices, tools, and workflows for building, deploying, monitoring, evaluating, and continuously improving production LLM applications.
Developer · Advanced
LLMOps vs MLOps
Complete comparison of LLMOps and MLOps — lifecycle, data, evaluation, monitoring, deployment, cost, failure modes, and what AI engineers need to know.
Developer · Advanced
How to Evaluate LLM Applications
Metrics, test datasets, RAG evaluation, agent evaluation, LLM-as-judge, production monitoring, and pre-launch checklists for production AI teams.
Developer · Career
AI Engineering Course
Public live-online AI Engineering: 40 hours of live classes plus 40 hours of project/lab work, with five portfolio builds. Review prerequisites, cohort availability and delivery terms.
Corporate · Advanced
Production AI Engineering
Corporate developer training in RAG, agents, MCP, evaluation and deployment. Compare the current 40-hour programme and the agreed lab scope on the course page.
Developer · Career
1:1 AI Engineering Mentorship
Explore individual guidance, project review and an agreed learning plan. Check current availability, duration, inclusions and fees on the programme page or with the team.
Corporate
Corporate AI Training
Customised AI training programmes for organisations — covering GenAI, ChatGPT, prompt engineering, data analytics, and AI automation for business teams.
Corporate · Developer
RAG Training India
Corporate RAG training for developer teams building retrieval-augmented generation systems in production.
Corporate · Developer
LangChain Training India
Corporate LangChain and LangGraph training for teams building production LLM applications.
Corporate · Developer
Claude AI Training Course
Live Claude AI training course covering Claude Chat, Claude Code, connectors, MCP concepts, business productivity workflows by department, and developer AI adoption.
Beginner · Corporate
Free Claude Training
Free introductory Claude AI training session — basics, prompting, document analysis, productivity workflows. Beginner-friendly. Register to join the next available session.
Corporate
ChatGPT Enterprise Training
ChatGPT Enterprise training for organizations — role-based workflows, Apps in ChatGPT, company knowledge, governance, responsible AI and enterprise rollout planning.
Corporate
Claude Enterprise Training
Claude Enterprise training for teams — Claude Chat, Cowork, Claude Code, connectors, MCP, shared projects, governance and organizational adoption planning.
Corporate · Beginner
ChatGPT Apps and Connectors Guide
A complete guide to ChatGPT Apps and connectors — how they work, app types (file search, sync, deep research, custom/MCP), company knowledge, permissions, admin controls, security and enterprise use cases.
Corporate · Developer
Claude Connectors Guide
A complete guide to Claude connectors — connector types (remote, desktop extensions, custom MCP), permission model, enterprise-managed auth, evaluation checklist, security considerations and responsible adoption.
Choose the format that answers your question
| Situation | Approach | What to check |
|---|---|---|
| “What does this term mean?” | Glossary definition | Example and nearby concepts |
| “How should I build or compare this?” | Practical guide | Decisions, project and tests |
| “I want structured instruction” | Course or team-training page | Prerequisites, format and curriculum |
Your reading-to-building plan
Make a three-resource learning shortlist
Choose one foundational explanation, one implementation guide and one evaluation guide for a fictional project.
What to produce
- A one-sentence project goal.
- Three resources and the question each answers.
- One small artifact to produce after reading.
Acceptance checks
- Each resource serves a different need.
- The task is small enough to attempt.
- There is a way to inspect the result.
- Further reading follows an observed gap.
This is an illustrative learning exercise, not a client case study or a measured outcome.
Common questions
Where should a complete beginner start?
Start with the roadmap and assess your programming foundation. Use the glossary for unfamiliar terms, then build small programs before a multi-component AI application.
Are the guides a substitute for checking product documentation?
No. They teach concepts and decisions. Follow the linked primary documentation for implementation details that depend on the version or service you use.
Continue learning
Prefer a guided learning path?
Explore the live-online AI Engineering course, its prerequisites and portfolio work. Choose training based on the skills you need to practise, not a promised job outcome.
Explore the AI Engineering course →Sources and further reading
Examples and decision frameworks are original teaching material. Product-specific implementation details should be checked against the version you use.