Beginner
Enrolling
👋 Viveka Sharma
AI Agents & Engineering 10 Weeks Cohort
A 10-week live, hands-on program to understand and build modern AI agent systems—from tools and MCP to memory, evaluation, multi-agent systems, and a final agentic AI project.
∞Seats
12Modules
2Projects
What you will learn and build
The full curriculum, module by module, with hands-on project steps along the way.
1
Week 1 - What Is an AI Agent?
Understand what makes an AI system an agent and how agents move beyond simple question-answering. Covers: what AI agents are, how agents differ from traditional LLM applications, goals and actions, function calling, and how models interact with external tools. Build: create a simple tool-using agent that can receive a goal, call a tool, and return a useful result.
2
Week 2 - MCP & Agent Memory
Let agents connect to external systems while maintaining useful context. Covers: Model Context Protocol (MCP), tools and resources, MCP hosts, clients and servers, agent memory, context and state. Build: connect an agent to an external tool through MCP and maintain relevant context across interactions.
3
Week 3 - The AI Agents Stack
Understand the layers that make modern agent systems work beyond the model itself. Covers: models, tools, memory, orchestration, agent runtimes, supporting infrastructure, and why agents can fail when moving from demos to production. Build: map the architecture of an AI agent system and identify the role of each layer.
4
Week 4 - Agent Architectures
Choose the right agent pattern for the problem instead of adding agents unnecessarily. Covers: single-agent patterns, Agentic RAG, Computer-Using Agents (CUA), Agent-to-Agent (A2A), and different approaches to agent workflows. Build: design an agent workflow for a real-world use case and explain the architecture behind it.
5
Week 5 - Prompt Engineering & Guardrails
Give agents clear instructions while keeping their actions within defined boundaries. Covers: agent prompt engineering, task and tool instructions, constraints, guardrails, and controlling unwanted agent behavior. Build: create an agent with structured instructions, tool-use rules, and guardrails for a multi-step task.
6
Week 6 - Agent Evaluation
Measure whether an agent actually works reliably—not just whether its responses look convincing. Covers: evaluations, evaluation criteria, testing agent behavior, failure cases, and reliability. Build: create an evaluation set for an agent and test its behavior across realistic scenarios.
7
Week 7 - AI Coding Tools
Understand how AI coding tools are changing software development workflows. Covers: Cursor vs Claude Code, how AI coding environments work, how coding agents interact with codebases, and different approaches to AI-assisted development. Build: use an AI coding workflow to complete, modify, and review a practical development task.
Project
Week 8 - AI Coding & Agent Toolkit
Explore the growing toolkit around AI-assisted software development and agent building. Covers: CodeRabbit, OpenAI Codex, recent changes in AI coding tools, open-source agent toolkits, and approaches for evaluating these tools. Build: use multiple AI development tools on a practical task and compare how their workflows differ.
8
Week 9 - Agent Memory & Multi-Agent Systems
Project
Final Agentic AI Project
Bring the complete agent-building workflow together around a practical problem. Covers: agent architecture, tools, MCP, memory, prompting, guardrails, evaluation, and system design. Build: design and present an end-to-end agentic AI solution, explain its architecture, and demonstrate how you would evaluate it.
9
Introduction to AI Engineering & the GenAI Landscape
Live session · Mentor-led · 1 hr, hands-on: What is an AI Engineer?; AI vs ML vs Deep Learning vs GenAI; The Modern AI Stack; Where LLMs Fit In; Capabilities & Limits of GenAI; Common AI Application Patterns; Responsible & Ethical AI; The AI Product Lifecycle; Roles in an AI Team; Industry Use Cases
10
Development Environment & Working with LLM APIs
Live session · Mentor-led · 1 hr, hands-on: Python Environment & Virtualenv; Notebooks vs Scripts; Managing API Keys & Secrets; Anatomy of an LLM API Call; Requests, Responses & Tokens; Temperature & Sampling; Streaming Responses; Rate Limits & Error Handling; Cost Awareness; Examples: OpenAI, Claude, Open Endpoints
11
Python for AI Engineers
Live session · Mentor-led · 1 hr, hands-on: Functions, Modules & Packages; Working with JSON; Type Hints & Dataclasses; Async Basics for API Calls; Environment Variables; Logging; Reading & Writing Files; Calling REST APIs; Clean Code for AI Apps
12
Data Handling for AI
Live session · Mentor-led · 1 hr, hands-on: NumPy Arrays & Vectors; Pandas DataFrames; Loading CSV, JSON & Parquet; Cleaning & Missing Values; Filtering & Aggregation; Basic Visualization; Train and Test Concepts; Working with Text Data; Data Quality for AI
Common questions
Is this live or recorded?Live, scheduled sessions with your trainer and cohort. Your trainer adds the class recording, files and notes to the classroom afterwards, so you can catch up if you miss one.
What do I get at the end?Finish the cohort to unlock a verifiable CareerByteCode certificate, 5 exam passes and 5 ByteLabs projects, plus your shipped project work in a public portfolio.
How is the price shown?The price is the base plus 18 percent GST, shown all-in. You pay securely via Razorpay.
Do I need experience?Pick a cohort at your level (Beginner here). Your trainer supports you through every module and project.
See student reviews →