Merge pull request #4 from ckavili/main

✨docs updated ✨

content/modules/ROOT/nav.adoc

@@ -12,19 +12,19 @@
 ** xref:02-04-why-should-care-agents.adoc[2.3 Why is it important to my organization?]
 
 * 3. Advance LLM Patterns
-** xref:03-01-advance-llm-patterns.adoc[4.1 Non-Agentic Patterns]
-** xref:03-02-tools-usage.adoc[4.2 Tools Usage from LLM Perspective]
-** xref:03-03-chain-of-thought.adoc[4.3 Chain of Thought]
-** xref:03-04-react-prompting.adoc[4.4 React Prompting]
-** xref:03-05-rag.adoc[4.5 Retrieval Augmented Generation (RAG)]
+** xref:03-01-advance-llm-patterns.adoc[3.1 Non-Agentic Patterns]
+** xref:03-02-tools-usage.adoc[3.2 Tools Usage from LLM Perspective]
+** xref:03-03-chain-of-thought.adoc[3.3 Chain of Thought]
+** xref:03-04-react-prompting.adoc[3.4 React Prompting]
+** xref:03-05-rag.adoc[3.5 Retrieval Augmented Generation (RAG)]
 
 * 4. Agentic AI Frameworks
-** xref:04-01-ai-agent-frameworks.adoc[3.1 AI Agents Frameworks]
-** xref:04-02-langgraph.adoc[3.2 LangGraph]
-** xref:04-03-autogen-framework.adoc[3.3 AutoGen Framework]
-** xref:04-04-crew-ai.adoc[3.4 CrewAI]
-** xref:04-05-llama-index.adoc[3.5 LlamaIndex]
-** xref:04-06-bee.adoc[3.6 Bee]
+** xref:04-01-ai-agent-frameworks.adoc[4.1 AI Agents Frameworks]
+** xref:04-02-langgraph.adoc[4.2 LangGraph]
+** xref:04-03-autogen-framework.adoc[4.3 AutoGen Framework]
+** xref:04-04-crew-ai.adoc[4.4 CrewAI]
+** xref:04-05-llama-index.adoc[4.5 LlamaIndex]
+** xref:04-06-bee.adoc[4.6 Bee]
 
 * 5. Agentic-AI-Based Integrations
 ** xref:05-01-what-is-an-ai-agent.adoc[5.1 What is an AI Agent?]

content/modules/ROOT/pages/01-02-current-process.adoc

@@ -74,7 +74,9 @@ focus on innovation.
 ### **Next Steps**  
 
 Crystal Sphere Insights aims to explore **agentic AI solutions** to address these challenges. 
+
 Proposed improvements include:  
+
 - Automating repetitive data handling and troubleshooting tasks.  
 - Enhancing client interaction workflows using natural language processing and intelligent automation.  
 - Integrating real-time feedback systems to improve report quality and portal functionality.  

content/modules/ROOT/pages/03-01-advance-llm-patterns.adoc

@@ -2,24 +2,24 @@
 include::_attributes.adoc[]
 :slide:
 
-In this section, we explore common patterns in LLM applications that enhance the model's capabilities without relying on agent-based control flows. These non-agentic patterns focus on leveraging the strengths of LLMs in structured and predictable ways.
+Before diving into Agentic AI, let's we explore common patterns in LLM applications that enhance the model's capabilities without relying on agent-based control flows. These non-agentic patterns focus on leveraging the strengths of LLMs in structured and predictable ways.
 
-== 4.1 Chain of Thought
-- Fosters logical reasoning by prompting the LLM to break down tasks step-by-step.
-- Improves coherence and context retention in multi-step problem-solving scenarios.
-- Enhances the model's ability to generate structured, sequential responses.
-
-== 4.2 Tools Usage from LLM Perspective
+== 3.2 Tools Usage from LLM Perspective
 - Involves the LLM invoking external tools (e.g., APIs, search engines) to gather information.
 - Supports tasks requiring real-time data retrieval, complex computations, or system interactions.
 - Extends the LLM's functionality beyond its static training data.
 
-== 4.3 ReAct Prompting
+== 3.3 Chain of Thought
+- Fosters logical reasoning by prompting the LLM to break down tasks step-by-step.
+- Improves coherence and context retention in multi-step problem-solving scenarios.
+- Enhances the model's ability to generate structured, sequential responses.
+
+== 3.4 ReAct Prompting
 - Combines reasoning and action steps, guiding the LLM to think and act iteratively.
 - Uses a Thought → Action → Observation loop for dynamic task execution.
 - Enhances decision-making by integrating external information into the reasoning process.
 
-== 4.4 Retrieval Augmented Generation (RAG)
+== 3.5 Retrieval Augmented Generation (RAG)
 - Merges information retrieval with response generation, grounding the LLM’s answers in real-time data.
 - Retrieves relevant documents or knowledge snippets to enhance response accuracy.
 - Ideal for applications needing up-to-date or domain-specific information, reducing hallucination risks.

content/modules/ROOT/pages/04-01-ai-agent-frameworks.adoc

@@ -3,6 +3,8 @@ include::_attributes.adoc[]
 
 == Introduction to AI Agent Frameworks
 
+Building on the structured and predictable ways we enhance LLM capabilities in previous section, AI agent frameworks take these patterns a step further by enabling models to act autonomously. While techniques like Chain of Thought, ReAct Prompting, and RAG improve reasoning, retrieval, and interaction, agentic systems orchestrate these capabilities to manage workflows, make decisions, and dynamically respond to complex environments.
+
 AI agent frameworks provide a foundation for building systems where intelligent agents can autonomously interact, make decisions, and perform tasks within a defined environment. These frameworks are becoming essential tools for developers, enabling them to create agents capable of reasoning, learning, and adapting to complex scenarios. Agents within these frameworks often act independently or collaboratively, fulfilling roles from simple task automation to complex decision-making in real-time.
 
 image::02/02-01-agentic-vs-non-agentic.png[AI Agents Diagram]

content/modules/ROOT/pages/04-02-langgraph.adoc

@@ -21,7 +21,7 @@ For our upcoming workshop, **we will be using LangGraph** to demonstrate the pot
 
 == LangGraph in Action! - Example
 
-As a sneak peak around the capabilities of LangGraph, please check out:
+As a sneak peak around the capabilities of LangGraph, please check out the examples:
 
-* link:https://github.com/rh-aiservices-bu/agentic-workshop/blob/main/lab-materials/07-agent-frameworks/7.1-tool-calling-langgraph-granite3.ipynb[LangGraph Example]
-* link:https://github.com/rh-aiservices-bu/agentic-workshop/blob/main/lab-materials/07-agent-frameworks/7.2-react-agents-langgraph-granite3.ipynb[LangGraph ReAct Example]
+* link:https://github.com/rh-aiservices-bu/agentic-examples/blob/main/frameworks/langgraph/tool-calling-langgraph-granite3.ipynb[LangGraph Example]
+* link:https://github.com/rh-aiservices-bu/agentic-examples/blob/main/frameworks/langgraph/react-agents-langgraph-granite3.ipynb[LangGraph ReAct Example]

content/modules/ROOT/pages/04-03-autogen-framework.adoc

@@ -21,4 +21,4 @@ include::_attributes.adoc[]
 
 As a sneak peak around the capabilities of AutoGen, please check out:
 
-* link:https://github.com/rh-aiservices-bu/agentic-workshop/blob/main/lab-materials/07-agent-frameworks/7.1-tool-calling-autogen-granite3-system.ipynb[Autogen Example]
+* link:https://github.com/rh-aiservices-bu/agentic-examples/blob/main/frameworks/autogen/tool-calling-autogen-granite3-system.ipynb[Autogen Example]

content/modules/ROOT/pages/04-04-crew-ai.adoc

@@ -34,4 +34,4 @@ at scale in production environments.
 
 As a sneak peak around the capabilities of CrewAI, please check out:
 
-* link:https://github.com/rh-aiservices-bu/agentic-workshop/blob/main/lab-materials/07-agent-frameworks/7.1-tool-calling-autogen-granite3-system.ipynb[CrewAI Example]
+* link:https://github.com/rh-aiservices-bu/agentic-examples/tree/main/frameworks/crewAI[CrewAI Example]

content/modules/ROOT/pages/04-06-bee.adoc

@@ -20,4 +20,4 @@ The Bee Agent Framework enables scalable, agent-based workflows compatible with
 
 As a sneak peak around the capabilities of Bee, please check out:
 
-* link:https://github.com/rh-aiservices-bu/agentic-workshop/blob/main/lab-materials/07-agent-frameworks/7.1-tool-calling-autogen-granite3-system.ipynb[Bee Example]
+* link:https://github.com/rh-aiservices-bu/agentic-examples/tree/main/frameworks/bee[Bee Example]

content/modules/ROOT/pages/05-01-what-is-an-ai-agent.adoc

@@ -1,53 +1,55 @@
-= What is an AI Agent
-include::_attributes.adoc[]
-:slide:
+= **What is an AI Agent?**  
+include::_attributes.adoc[]  
+:slide:  
 
-== Overview
+== **Overview**  
 
-An Agent is an autonomous system that leverages Large Language Models (LLMs) to perform tasks by understanding, 
-reasoning, planning, and executing actions with minimal human intervention. AI agents are designed to break down 
-complex problems into manageable steps, utilizing tools, accessing memory, and adapting their behavior based on the 
-provided context.
+An **AI Agent** is an autonomous system that utilizes **Large Language Models (LLMs)** to understand, reason, plan, and execute tasks with minimal human intervention. Unlike traditional AI models that respond passively to prompts, agents **actively break down complex problems into manageable steps**, leveraging memory, external tools, and adaptive behavior to achieve their goals.  
 
-At its core, an agent is structured to:
+At its core, an AI agent follows a structured process:  
 
-1. **Receive a Task**: The agent takes input from the user, such as a question or command.
-2. **Plan a Solution**: The agent decomposes the problem, chooses appropriate tools, and reasons through possible solutions.
-3. **Execute the Plan**: It performs actions, such as retrieving information, using tools, or generating responses based on the devised plan.
-4. **Deliver Results**: Finally, it presents the solution or output in a structured, actionable format.
+1. **Receive a Task** → Takes user input (e.g., a command or question).  
+2. **Plan a Solution** → Decomposes the problem, selects tools, and reasons through possible solutions.  
+3. **Execute the Plan** → Retrieves information, performs computations, or interacts with external resources.  
+4. **Deliver Results** → Presents a structured response, action, or decision.  
 
-image::02/02-01-agentic-vs-non-agentic.png[AI Agents Diagram]
+image::02/02-01-agentic-vs-non-agentic.png[AI Agents Diagram]  
 
-== Key Components of an AI Agent:
+== **Key Components of an AI Agent**  
 
-- **Profiling Module (Agent Core)**: This is the agent's decision-making hub. It defines the role and goals of 
-the agent (e.g., financial analyst, teacher), selects appropriate tools, and coordinates task execution. 
-The agent's "profile" helps determine its behavior and interaction style based on its role.
+An AI agent is composed of several **interconnected modules**, each responsible for specific functions that enable decision-making and execution.  
 
-- **Memory Module**: The agent uses memory to track past interactions and experiences. Short-term memory stores 
-context-relevant information (e.g., current session details), while long-term memory retains important information 
-over time, which the agent can refer back to when needed.
+- **Profiling Module (Agent Core)** 🏗️  
 
-- **Tools Module**: External resources (e.g., APIs, databases) that the agent can call upon to complete tasks, 
-like retrieving real-time data, performing calculations, or interacting with other systems.
+  Defines the agent’s **role, goals, and behavior** (e.g., financial analyst, teacher, assistant). This module selects tools, orchestrates task execution, and determines how the agent interacts with users.  
 
-- **Planning Module**: This module allows the agent to break down complex tasks into smaller, manageable sub-tasks. 
-By planning step-by-step, the agent can tackle intricate queries and tasks with greater efficiency and precision.
+- **Memory Module** 🧠  
 
-image::02/02-02-agentic-components.png[AI Agents Diagram]
+  Stores past interactions and contextual data:  
+  - **Short-term memory**: Tracks current session details for immediate recall.  
+  - **Long-term memory**: Retains historical information to improve continuity across interactions.  
 
-== Anatomy of an AI Agent:
+- **Tools Module** 🔧  
 
-The Anatomy of an AI Agent consists of interconnected components such as: 
+  Connects the agent to **external resources** such as APIs, databases, or third-party services. This enables real-time data retrieval, calculations, and interaction with other systems.  
 
-1. Persona 
-2. Instruction
-3. Task & Planning
-4. Memory 
-5. Tools
-6. Delegation
+- **Planning Module** 📌  
 
-which collectively enable the agent to perform tasks, manage strategies, and make 
-decisions effectively within its defined context.
+  Breaks down complex tasks into **smaller, manageable steps** to ensure structured decision-making and execution. This step-by-step reasoning improves efficiency and precision.  
 
-image::05/05-06-agent-framework.png[Agentic Integrations]
+image::02/02-02-agentic-components.png[AI Agents Diagram]  
+
+== **Anatomy of an AI Agent**  
+
+An AI agent’s functionality is driven by the following key elements:  
+
+1. **Persona** → Defines the agent’s identity and role.  
+2. **Instruction** → Guides the agent on how to operate.  
+3. **Task & Planning** → Helps the agent break down and structure its workflow.  
+4. **Memory** → Allows it to recall and learn from past interactions.  
+5. **Tools** → Expands its capabilities by interacting with external systems.  
+6. **Delegation** → Enables collaboration with other agents or processes.  
+
+Together, these components empower AI agents to reason, strategize, and autonomously complete tasks within a defined context.  
+
+image::05/05-06-agent-framework.png[Agentic Integrations]  

lab-materials/02-tools/2.3-react-prompting-granite3.ipynb

@@ -25,7 +25,7 @@
     "\n",
     "This loop continues until the model has gathered enough information to generate a complete, accurate response or decides that no further actions are required.\n",
     "\n",
-    "image::04/04-02-react-diagram.png[ReAct Diagram]"
+    "![LLM Tools](../../content/modules/ROOT/assets/images/04/04-02-react-diagram.png)"
    ]
   },
   {