Bootcamps All Levels English Special Launch Offer

5-Day AI Engineering Bootcamp (English)

Name: 5-Day AI Engineering Bootcamp (English)
Price: 499 INR
Availability: InStock

From learning AI to building real AI applications. 5 real AI projects in 5 days, taught live in English.

Designed & taught byDinesh Kushwaha FormatLive online via Zoom

Duration: 5 days · 3 live + 2 practice
Next batch: 5 October 2026
Schedule: Mon, Wed & Fri · 8:00–9:30 PM IST
Cohort: Limited seats, next batch starting soon
Taught in: English

₹499~~₹4,999~~Save 90%

You save ₹4,500 with the current offer.

Choose how to pay Pay in full ₹499 One payment Pay in 2 parts ₹250 now 50% + 50% ₹250 today ₹249 in 14 days

Remaining instalments are paid online from your account; we email a reminder before each due date.

Ask a question

Next batch starts 5 October 2026

This course includes

5 real AI projects, step by step
3 live classes + 2 hands-on practice sessions (1.5 hours each)
All learning resources: code, templates and guides
Session recordings with lifetime access
Certificate from a registered company
Supportive community

Secure checkout powered by Razorpay. Pay with UPI, cards, net banking or wallets.

What you'll walk away with

Build AI apps with OpenAI, Claude and Gemini
Chat with your own documents using RAG
Connect AI to real tools and APIs
Build agents that reason and use tools with MCP
Ship an end-to-end AI application for your portfolio

Who it's for

Software engineers, developers, tech leads and managers, early-career engineers moving into AI, college graduates who want job-ready AI skills, and founders, product builders and curious learners.

Curriculum

From learning AI to building real AI applications. You build five real AI projects in five days, through three live classes and two hands-on practice sessions of 1.5 hours each, taught live in English by Dinesh Kushwaha.

Day 1 · Monday · Live Session (1.5 hrs): LLMs & RAG, AI Knowledge Assistant + AskMyDocs AI

Understand how large language models work with OpenAI, Claude and Gemini, then ground them in your own data with RAG. Build an assistant you can chat with about your documents, then turn it into your own document Q&A assistant.

How LLMs work: OpenAI, Claude and Gemini
- Understand how modern LLMs work, including OpenAI, Claude, and Gemini — tokens, context windows, inference, parameters, prompting, and model capabilities.
- Hands-on Platform: Google Gemini — selected for its accessible API and free-tier availability, making it convenient for students to practice without requiring a paid LLM subscription.
Prompt engineering that holds up in real use.
- System Prompt vs. User Prompt
- Good vs. Bad Prompts — Why They Work or Fail
- Context, Constraints & Output Control
Embeddings, vector search and RAG
- Hands-on RAG App: Gemini Embeddings + Chroma Vector Database + Streamlit UI

Hands-on project: Two projects: AI Knowledge Assistant (chat with your own documents) and AskMyDocs AI (your own document Q&A assistant).

Day 2 · Tuesday · Practice Session: Guided Self-Practice | Build · Practice · Ask · Apply

Apply the concepts from the Live Session through hands-on practice and continue building your AI application.

Hands-On Practice — Implement the concepts covered in the Live Session
Build & Experiment — Work with Gemini, Embeddings, Chroma & Streamlit
Ask When You’re Stuck — Get guidance on questions, errors, and implementation challenges
Learn Through Problems — Understand the reasoning behind solutions and improve your implementation
Keep Building — Apply the guidance and continue developing your AskMyDocs AI / RAG application

Hands-on project: Learn → Build → Get Stuck → Get Unblocked → Build Further

Day 3 · Wednesday · Live Session (1.5 hrs) : AI Task Assistant

Combine everything so far into one application, with step-by-step guidance.

Understand AI Tools
- What are tools and why do AI applications need them?
- Create simulated tools from scratch without using a framework
- Use Google Gemini to understand how an LLM works with tools
Tool Selection & Execution
- Understand how Gemini determines which tool to use
- Explore the complete tool selection → execution → result → response flow
- Work with tool inputs, outputs, and error handling
Build Tools with LangChain
- Create tools using LangChain, an open-source framework
- Connect Gemini + LangChain Tools
- Understand what the framework handles behind the scenes
Understand How AI Agents Work
- What makes an Agent different from a traditional LLM application?
- Understand the reason → select tool → execute → observe → continue loop
- Build an Agent from scratch without using an agent framework
Hands-On Application — AI Agent
- Connect your custom tools to the Agent
- Use Gemini + Tools + Agent logic
- Build a working AI Agent application

Hands-on project: Gemini → Tools → Tool Selection → Tool Execution → LangChain Tools → Agent Logic → AI Agent Application. AI Task Assistant, a chat tools application.

Day 4 · Thursday · Practice Session: Guided Self-Practice | Build · Practice · Ask · Apply

Continue practicing the concepts and application from the Day 3 Live Session.

Hands-On Practice
- Implement Gemini + Tools + Agent concepts independently
- Experiment with simulated and LangChain-based tools
Build & Experiment
- Connect tools to your Agent
- Test different tool-selection and execution scenarios
- Extend the AI Agent application with additional capabilities
Ask When You’re Stuck
- Clarify questions while implementing
- Get guidance on errors, tool integration, agent logic, and implementation challenges
- Understand the why behind the solution and continue building
Apply & Improve
- Refine your Agent implementation
- Experiment with different workflows and use cases
- Strengthen your understanding through hands-on practice

Hands-on project: Build → Experiment → Ask → Understand → Improve – AI Agent Copilot, which reasons and uses tools with MCP.

Day 5 · Friday · Live Session (1.5 hrs): MCP + Guardrails + Evaluation + Tracing & Observability

Move from building AI agents to understanding how to make them more reliable, controlled, and observable in real-world applications.

Model Context Protocol (MCP)
- Understand what MCP is and why it matters
- Learn how AI applications connect with external tools and data through a standard protocol
- Understand the roles of MCP Client, MCP Server & Tools
- Build a simple MCP-based integration
Guardrails for AI Applications
- Why AI applications need guardrails
- Control inputs, outputs, tool usage, and application behavior
- Understand practical approaches for safer and more predictable AI workflows
Evaluation
- Why a working AI application is not necessarily a reliable AI application
- Evaluate answer quality, relevance, correctness, and tool execution
- Create practical evaluation scenarios for your AI application
Tracing & Observability
- Understand what happens inside an AI workflow
- Trace LLM → Retrieval → Tool → Agent → Response
- Identify failures, latency, and unexpected behavior

Hands-on project: LLMs → RAG → Tools → Agents → MCP → Guardrails → Evaluation → Tracing → AI Executive Assistant

Tools & technologies

OpenAIClaudeGeminiRAGLangChainLangGraphTools & APIsMCP

Your instructor

Dinesh Kushwaha

Founder, Dinesh AI Academy · Principal Software Engineer & Application Architect

Dinesh has spent 18+ years architecting and delivering 50+ enterprise-scale platforms and has coached more than 1,000 engineers. He teaches AI the way he builds it: practical, secure, and focused on what works in production.

Read Dinesh's story

Keep Exploring