Applied Agentic AI: Systems, Design & Impact Bootcamp

Applied Agentic AI: Systems, Design & Impact Bootcamp

In collaboration with Microsoft 

• • Build advanced knowledge in multi-agent systems, RAG, MCP, and related technologies.
  • Design and develop next-generation agentic AI solutions using industry-leading frameworks.
  • 10 weeks bootcamp program (online class every weekend!)

• Ask us for next cohort schedule details!

The Applied Agentic AI: Systems, Design & Impact programme is designed to guide you through the emerging field of agentic AI. It combines Microsoft’s AI technology expertise with instructor-led training, live online sessions, and hands-on projects.

The programme takes you beyond interface development to designing intelligent behaviours. You’ll explore agentic frameworks, planning systems, multi-agent coordination, and prompt engineering, while working on real-world projects with industry-standard tools. By completion, you’ll be able to orchestrate multi-agent systems, develop AI-native product strategies, and lead AI-driven transformation within your organisation.

Why is Agentic AI Critical Today?

AI has moved beyond experimental stages, with companies now deploying it at scale to enhance productivity and transform products. This shift has created an urgent need for professionals who can actively lead AI initiatives rather than just observe them.

The next frontier is agentic AI and multi-agent systems—AI capable of planning, decision-making, and acting across complex workflows. Organisations are rapidly investing in AI agents, fundamentally changing product development and work processes. This trend presents a significant opportunity for mid- to senior-level product managers and technology leaders, as roles that combine product expertise with agentic AI skills are becoming highly sought-after and well-compensated in the AI ecosystem.

Key Features

• Course and material in English
• Beginner - Advanced level
• 10 weeks program (6-8 hours/ week. Weekend classes)
• 70+ hours of live online classroom 
• 200+ hours recommended study time 
• 1 year of access to the learning platform & class recordings
• 25+ Tools and Frameworks: LangChain, AutoGen, CrewAI, n8n, Hugging Face, LangSmith, Jupyter, and more
• 40+ demos, 10+ guided practices, 11 frameworks
• 7 hands-on course-end projects, and 1 capstone
• Get Microsoft Learn portal access and MS-branded certificates.
• Certificate for each courses & bootcamp master certificate included

13+ Skills Covered

• Workflow Automation
• Agentic Frameworks
• MultiAgent Systems
• Intelligent Automation
• GTM for Agentic AI
• Ethics and Transparency
• LLM Function Calling
• Planning Systems
• Prompt Engineering
• UIUX Agentic AI
• Copilots
• MCP
• RAG

Engaging Learning Experience

• Peer Interaction
  Enjoy a true classroom-like environment by connecting with fellow learners and engaging with mentors in real time through Slack.
• Flexible Learning
  Never fall behind—access recorded sessions anytime to catch up and stay aligned with your cohort.
• Mentorship Sessions
  Receive expert support from mentors to resolve doubts, get project guidance, and enhance your learning journey.
• Dedicated Support
  Benefit from a Cohort Manager who provides personalized assistance and ensures you stay on track toward success.

Learning Outcome

• Understand and apply core concepts of agentic AI, including how autonomous agents reason, plan, and act within complex systems.
• Design and orchestrate multi‑agent AI systems using industry‑standard frameworks and tools.
• Use advanced planning systems, RAG (retrieval‑augmented generation), prompt engineering, and MCP (Model Context Protocol) to build efficient, scalable autonomous workflows.
• Translate strategic product vision into practical AI‑driven solutions that can coordinate multiple agents to solve real business problems.
• Work hands‑on with a broad set of AI tools (e.g., LangChain, AutoGen, CrewAI, n8n, LangSmith) to prototype, test, and refine agentic solutions.
• Evaluate and implement agentic system components with attention to UX, security, interoperability, and operational readiness.
• Measure performance, define key metrics, and assess ROI for AI agent deployments in production contexts.
• Develop and present a production‑grade capstone project that connects agent design with go‑to‑market strategy and operational execution

Target Group

It’s aimed at experienced professionals who want to design, orchestrate, and lead advanced AI systems that go beyond basic generative AI into multi‑agent orchestration and strategy

The Applied Agentic AI: Systems, Design & Impact course is primarily aimed at:

• Mid- to senior-level professionals who want to lead or manage AI-driven products and systems.
• Product managers and technical leaders seeking to integrate agentic AI into workflows and strategy.
• AI/ML practitioners and engineers looking to advance into multi-agent system design and orchestration.
• Consultants or innovators who advise on AI adoption, autonomous systems, or AI-driven business transformation.
• Professionals with a basic understanding of programming and an interest in agentic AI, planning systems, and multi-agent orchestration.

Prerequisites

• Be at least 18 years old and have a high school diploma or equivalent
• Have a fundamental understanding of programing concepts
• Have 4+ years of professional experience, preferred, but not mandatory

Bootcamp Curriculum

1. Python Refresher With AI (Optional)
2. Foundations of AI & Agentic AI
3. Generative AI Tech Stack and Prompt Engineering
4. LLM Internals & Planning Systems
5. Multi-Agent Ecosystems (I)
6. Multi-Agent Ecosystems (II)
7. Model Context & Tooling Protocol
8. Metrics, GTM & ROI
9. Agentic UX Design & Transparency
10. Dev Tools & Product Readiness
11. Develop AI Agents on Azure (Microsoft)
12. Capstone: Product Strategy Simulation 

Electives:

• Develop Generative AI Apps in Azure (Microsoft)
• Masterclass on Agentic AI Solutions Using Copilot Studio and AutoGen

Python Refresher With AI (Optional)

This course refreshes Python fundamentals for AI/ML, covering core constructs, environment setup, data structures, control flows, OOP, file handling, and AI-assisted coding tools like GitHub Copilot. Hands-on exercises in data manipulation and a capstone project comparing traditional and AI-enhanced coding prepare learners to apply Python effectively in modern AI workflows.

Skills developed:

• Python Programming 
• Data Manipulation
• Control Flow OOP Basics
• AI-Assisted Coding 
• IDEs & Development Environments

Tools and Frameworks Covered:

• Jupyter
• Visual Studio Code
• Google colab
• GitHub Copilot

Course-End Projects

• Analyzing Customer Orders With Python
• Building a Text-Based Adventure Game With GitHub Copilot

Foundations of AI & Agentic AI

This course introduces the Learn > Build > Deploy framework and explores the AI hierarchy (AI, ML, DL, GenAI, Agentic AI), transformer architectures, and autonomous AI agents. Key topics include influential papers like “Attention is All You Need”, CoT prompting, ReAct frameworks, and a 4-layer GenAI stack analogy. It provides essential knowledge for technical product management of AI systems, emphasizing both theoretical and practical agentic AI concepts.

Skills developed:

• AI Literacy
• GenAI Fundamentals
• Transformer Understanding 
• Prompting Techniques

Generative AI Tech Stack and Prompt Engineering

This course presents the Learn > Build > Deploy framework and explores the AI hierarchy, including AI, ML, DL, GenAI, and Agentic AI, along with transformer architectures and autonomous AI agents. It covers influential studies such as “Attention is All You Need”, CoT prompting, ReAct frameworks, and a 4-layer GenAI stack analogy, providing essential foundational knowledge for technical product management with a focus on both theoretical and practical agentic AI concepts.

Skills developed:

• GenAI Tech Stack Agent Orchestration
• Vector Databases
• AI UX Design
• Low-Code Prototyping

Tools and Frameworks Covered:

• Lovable
• Emergent
• LangChain
• LangGraph
• Crewai
• AutoGen

LLM Internals & Planning Systems

This course emphasizes product management productivity with AI, teaching prompt engineering and planning systems using LangChain and function-calling APIs. Live sessions cover building Q&A bots with API integration, designing agent-driven workflows, and advanced prompt strategies to optimize language model interactions. Hands-on labs focus on creating multi-step agents and integrating contextual tools, strengthening practical skills in agent-based product development.

Skills developed:

• Planning Systems Agent Workflow Design
• RAG Pipeline Design
• Multi-Step Reasoning
• Tool Integration

Tools and Frameworks Covered:

• Lovable
• Emergent
• ChatGPT
• crewAI
• LangGraph
• LangChain
• A2A
• Agentic RAG Design Frameworks

Guided Practices:

• Prototyping Product Ideas With AI Tools
• Building a Multi-Agent System for Feature Prioritisation

Demos:

• Debugging prompt failures in product feature summaries
• Applying CoT and ReAct prompting for drafting user stories and analyzing problems
• Building a RAG-powered FAQ agent with custom knowledge
• Building a finance Q&A agent using LangChain

Course-End Project:

• Building a RAG Pipeline With PDF Retrieval

Multi-Agent Ecosystems (I)

This course delves into advanced retrieval-augmented generation (RAG) systems and multi-agent architectures, using hands-on exercises with CrewAI and LangGraph. It covers agent collaboration patterns, role-based designs with YAML, memory management, and practical orchestration frameworks. Participants develop modular multi-agent teams emphasizing scalability, state handling, and autonomous information synthesis, with deliverables including presentations advocating modular agent architectures.

Skills developed:

• Multi-Agent Design RAG Architecture
• Memory Strategies
• Workflow Orchestration
• Agent Collaboration
• Analytical Reasoning

Tools and Frameworks covered:

• Crewai
• LangGraph
• A2A
• MetaGPT
• AutoGPT
• Agentic RAG design frameworks

Guided Practices:

• Generating Product Specs With MetaGPT
• Orchestrating AI Agents With LangGraph

Demos:

• Understanding the Anthropic Research Agent
• Building a CrewAI multi-agent system with RAG (chatbot)
• Executing serial and parallel workflows using CrewAI agents

Course-End Project: 

• Building an Agentic RAG Router System

Multi-Agent Ecosystems (II)

Building on core multi-agent concepts, this course focuses on enterprise-level agent orchestration using Microsoft AutoGen and n8n workflow automation. Topics include communication protocols, database integration, and strategies for production deployment. Projects involve creating scalable, high-performance, secure, and compliant marketing agent pipelines, while visual workflows and protocol analyses help learners master complex distributed agent systems.

Skills developed:

• Agent Orchestration 
• Workflow Automation
• Multi-Agent Communication
• Compliance
• Database integration

Tools and Frameworks covered:

• AutoGen
• N8n
• Docker
• Phoenix Frameworks
• LangSmith
• mongoDB
• PostgreSQL 
• Pinecone
• A2A
• Agentic RAG workflow patterns

Guided Practices:

• Building a Multi-Agent Support Triage System
• Designing Human-in-the-Loop Publishing Workflows

Demos:

• Installing and running AutoGen locally
• Using AutoGen for autonomous internal document QA & policy compliance
• Response format negotiation for multi-agent communication
• Integrating n8n for automated customer support ticket routing
• Implementing AutoGen agent chain for automated code testing & debugging

Course-End Project: 

• Building AI-Powered LinkedIn Automation With n8n

Model Context & Tooling Protocol

This course covers the Model Context Protocol (MCP) for standardizing and integrating AI tools. Key topics include structured context binding, interoperability standards, JSON schema design, secure tool hosting, and memory persistence. Hands-on labs guide the creation of contextual AI agents that chain outputs across tools with authentication and performance tuning. The focus is on enterprise readiness, security best practices, and making tools easily discoverable through standardized protocols.

Skills developed:

• Context Binding Tool Interoperability
• Schema Definition
• Performance Optimization
• Secure Tool Hosting

Tools and Frameworks covered:

• N8n
• GitHub
• Model Context Protocol
• FASTMCP

Demos:

• Building a MarketIntel MCP server for market research
• Building a research agent workflow with MCP server in n8n
• Response format negotiation for multi-agent communication
• Integrating n8n for automated customer support ticket routing
• Implementing AutoGen agent chain for automated code testing & debugging

Metrics, GTM & ROI

This course provides a complete framework for evaluating AI agent performance, covering OKRs, metrics such as success rate and latency, and ROI assessment. It explores observability tools like LangSmith and Phoenix, real-time logging, and conversational analysis. Business-focused topics include pricing, go-to-market strategies, and deploying agent MVPs with analytics dashboards. Hands-on exercises in instrumentation and monitoring prepare learners for operational excellence.

Skills developed:

• Agent Metrics Analysis Observability Setup
• A/B Testing
• GTM Strategy
• ROI Evaluation
• Agent Monitoring

Tools and Frameworks covered:

• LangSmith
• Miro

Demos:

• Setting up LangSmith tracing on a simple AI agent
• A/B testing AI responses with prompt variants
• Creating a Lean Canvas on Miro (collaborative exercise)

Agentic UX Design & Transparency

Focusing on user experience in AI products, this course explores interaction design for agentic UX, including flexible and probabilistic flows, managing ambiguity, and human-in-the-loop checkpoints. It addresses ethical challenges like hallucinations and bias, teaching guardrails, transparency methods, confidence indicators, and explainable interfaces. Learners develop full UX prototypes prioritizing trust, user control, and resilient fail-soft design.

Skills developed:

• UX Prototyping 
• AI-First Design
• Human-in-the-Loop Design
• UX for Human & AI Interaction
• UX Design for AI Risk Mitigation

Tools covered:

• Figma

Guided Practice:

• Designing Proactive Agent Behaviours in Figma

Demos:

• Creating a chat-style prototype in Figma
• Designing an interface with AI-suggested actions and user control buttons
• Creating a reasoning tooltip and a planned action in Figma
• Designing human-in-the-loop approval and feedback interfaces in Figma

Course-End Project: 

• Designing an Agentic UX Trust Prototype

Dev Tools & Product Readiness

This course, centered on deployment and live operations, explores cloud versus edge hosting, serverless and containerized environments, and model hosting approaches. It includes practical exercises with Firebase and n8n automation workflows, integrating feedback and testing systems for user insights, setting up alerts for monitoring, and an introduction to infrastructure-as-code with Terraform and Pulumi. Learners gain the skills needed to ensure scalable and maintainable AI product readiness.

Skills developed:

• Workflow Automation 
• Event Logging
• Infrastructure-as-Code
• Product Readiness
• Model Hosting

Tools covered:

• Hugging Face

Guided Practice:

• Building a Full-Stack Agent MVP in Colab

Demos:

• Log and visualize user–agent interaction events in Firestore
• Embed a Lovable feedback widget and track Firebase Analytics events
• Run a self-hosted open-source LLM locally using Ollama

Course-End Project: 

• Designing a Multi-Agent Workflow Planner

Develop AI Agents on Azure (Microsoft)

This course teaches how to build AI agents using Microsoft Azure’s cloud platform and tools. It covers Azure frameworks, deployment workflows, security integration, and scalable orchestration methods. Participants gain practical experience developing and hosting AI agents in Azure, with a focus on enterprise-level reliability and compliance.

Skills developed:

• Deployment on Azure 
• Cloud Orchestration
• Security Integration 
• Scalable Agent Design
• Enterprise Compliance 

Capstone Project: Product Strategy Simulation

The capstone project combines multi-agent system design with go-to-market strategy by creating a production-ready 4-agent market research and GTM framework using n8n and CrewAI, integrated with MCP. It emphasizes business strategy, including Lean Canvas, pricing, and acquisition planning, alongside performance monitoring and real-world chatbot deployment. This hands-on project equips learners for practical leadership in AI product development.

Skills developed:

• Multi-Agent System Design 
• MCP Integration
• GTM Planning 
• Pricing Strategy
• Performance Analytics 
• Real-World Deployment

Elective Courses

Elective 1: Develop Generative AI Apps in Azure (Microsoft)

This course equips you to develop AI solutions on Azure using Microsoft Foundry. You’ll learn to plan and configure AI environments, choose and deploy models from the catalog, build applications with the Foundry SDK, use prompt flows, create RAG solutions with your data, fine-tune models, apply responsible AI practices, and assess generative AI performance with Azure AI Studio tools.

Elective 2: Masterclass on Agentic AI Solutions Using Copilot Studio and AutoGen

This masterclass provides hands-on experience in designing and deploying agentic AI solutions using modern low-code and open-source frameworks. Through live sessions with industry experts, it demonstrates how tools like Copilot Studio and AutoGen can speed up development and enable fast deployment of agentic systems in practical business settings.

FAQ

How is the program delivered?

The course is delivered entirely online through live virtual classes, offering an 80:20 blend of experiential training and theoretical learning. You'll engage in hands-on projects, case studies, and interactive sessions led by industry experts.

How is the class schedule looks like? Is there recordings?

The course typically spans about 10 intensive weeks, with an estimated 6–8 hours of weekly weekend live sessions with a variety of schedules. In between courses, there will be a lot of hands-on project to complete. Please email us to get the details of the schedule of the program. If you miss a class, you can always watch the recording.

What is agentic AI, and how is it different from regular AI?

Agentic AI refers to autonomous systems capable of planning, reasoning, and acting across multiple tasks or workflows. Unlike traditional AI, which reacts to inputs, agentic AI can make decisions, coordinate with other agents, and adapt to dynamic environments, enabling complex problem-solving in real-world business contexts.

How does this course help in career growth?

Graduates gain skills in AI product strategy, multi-agent system orchestration, and AI-driven business leadership, preparing them for roles such as:

• AI Product Manager
• AI Solutions Architect
• Technical Lead for AI Systems
• AI Innovation Consultant
• Technology Strategy Manager

Do I need prior coding or AI experience?

No advanced programming or deep AI experience is required. A basic understanding of programming concepts and data workflows is sufficient. The course focuses on designing, orchestrating, and managing AI systems rather than building models from scratch.

Can I apply this knowledge in my current role?

Absolutely. The course emphasizes real-world applicability, enabling learners to design, deploy, and optimize agentic AI solutions in product development, marketing, customer service, and operational automation