Demo VPAT
Category : VPAT
Demo VPAT
Serverless computing is a cloud computing ...

Serverless computing is a cloud computing model that enables developers to create and deploy applications without the need to manage servers or infrastructure. One widely used implementation of serverless computing is through AWS Lambda, a compute service provided by Amazon Web Services (AWS). By using AWS Lambda, developers can execute code without the need to provision or maintain servers, only pay for the compute time used by the application, and automatically scale the application based on incoming requests.

When building a serverless application, some of the commonly utilized AWS services include AWS Lambda, AWS DynamoDB, AWS API Gateway, AWS SNS, and AWS SQS.

This guided project has the following topics

Module Topics
1 Creating Serverless Application using SAM
2 Serverless Synchronous Invocation
3 Serverless S3 Asynchronous Invocation
4 Serverless SNS Asynchronous Invocation
5 Serverless Error Handling
6 Exploration Zone

Prerequisites

  1. Familiarity with basics of AWS Services
  2. Knowledge about Python Programming using BOTO3

Learning Objectives

By completing this Guided Project, you will learn about

  1. Developing a serverless application.
  2. Using AWS Serverless Application Model to build and deploy the project.
  3. Create a Lambda function and store data in the DynamoDB.
  4. Configure S3 bucket data upload event as a trigger to the Lambda function.
  5. Publish the event as SNS Topic
  6. Configure SNS Topic as trigger to Lambda Function.
  7. Error Handling in Lambda Functions.

Skill Tags

  1. AWS Serverless Application
  2. AWS Python Developer
  3. AWS SAM

Scenario

Employee Appraisal Management Application

A company aims to create a web application that can manage employee information and publish their score/ratings. To meet their requirements, they plan to utilize AWS services.

To assist the company, we'll develop REST APIs using AWS Lambda to manage employee data in AWS DynamoDB. The employee score (JSON File) will be uploaded to an AWS S3 Bucket. Once uploaded, we'll calculate the employee grade and publish it to AWS SNS Topic. Additionally, an AWS Lambda function will update the employee information in DynamoDB with their grades when the grade is published. The application should have a robust error handling strategy to ensure that the application remains functional at all times.

HR Policy Chatbot using RAG
Category : HR & Recruitment
HR Policy Chatbot using RAG
Build and deploy a Policy Chatbot that...

Build and deploy a Policy Chatbot that can instantly, and reliably answer complex employee questions by citing the exact sections of HR policy documents.

Who Should Attend

HR Specialist, Global HR Team

Use Case

An AI system uses (Retrieval-Augmented Generation) RAG to search a database of HR policies and generate a concise answer while simultaneously providing the source location (page/section/document name) of the policy.

Core Challenges

Complexity & Volume: Policies are often fragmented, cross-referenced, and contained in massive, diverse document types (PDFs, Word docs).
Accuracy/Trust: Answers must be 100% accurate and verifiable, as misinterpretation of HR policy can lead to compliance issues.
Scalability: HR teams can't scale to handle a global volume of policy-related inquiries manually.

Tools & Activities:

The course explores 

    • How to setup a RAG architecture to explore an HR Policy document and ground the respond within the information available in a given input (HR Policy document)
      • Document Ingestion and Chunking Strategy, Vector Database Setup and Indexing, Implementing the RAG Workflow
    • Prompt Engineering.
    • Interacting with an LLM through the chat interface
    • Pinecone vector database configuration, chunking and storage, search and retrieval
    • n8n workflow automation
    • Building a Chat interface

Outcome

Participants will gain the skills to deploy a Trustworthy, Authoritative HR Policy Chatbot, leading to significantly reduced HR workload, instant 24/7 availability, and improved compliance through standardized policy interpretation.

RAG for Medical Literature Q&A
Category : Healthcare
RAG for Medical Literature Q&A
To understand and implement Retrieval-...

To understand and implement Retrieval-Augmented Generation (RAG) as a key architectural pattern for LLMs to deliver evidence-based, trustworthy Q&A from vast medical literature.

Use Case

Building and querying an AI system that leverages a proprietary medical knowledge base to provide referenced and highly accurate answers to clinical and research inquiries.

Core Challenges

Information Overload: Healthcare SMEs struggle to manually review thousands of new papers to stay current.

Slow Decision Support: Traditional search methods are slow and do not provide concise, synthesized answers with source evidence.

Hallucination Risk: Typical / standard LLMs could respond with inaccurate or fabricated information.

Tools & Activities:

The course explores 

    • How to setup a RAG architecture to explore a medical paper and ground the respond within the information available in a given input (pdf research paper)
    • Prompt engineering.
    • Interacting with an LLM through the chat interface
    • Pinecone vector database configuration, chunking and storage, search and retrieval
    • n8n workflow automation

Outcome

Participants will gain the skills to deploy a trustworthy, evidence-based AI system that ensures high factual accuracy and provides instant, referenced answers to complex clinical or research questions.


The 60-Second Bid: Market Intelligence with n8n & AI
Category : How To
The 60-Second Bid: Market Intelligence with n8n & AI
This course is a fast-paced, Practice Proj...

This course is a fast-paced, Practice Project designed specifically for non-technical functional leaders who need to drive efficiency and introduce intelligent automation into your operations.

The core goal is to empower participants to build AI Agents within the n8n low-code platform. You will learn to transform raw, unstructured data (e.g. datasets, reports, narratives, and emails) into structured, actionable intelligence using advanced AI and routing logic.

The learning is centered around the implementation of a Capstone Workflow that is provided fully configured in your lab environment. Across the modules, you will systematically explore the architecture of this working AI Agent, and understand its logic. 

Outcome from this Course

Upon completing this hands-on course, participants will be able to:

  1. Build and Deploy Intelligent Workflows: Confidently design and implement functional, low-code automation workflows using n8n, integrating logic, data sources, and external APIs.

  2. Master Prompt Engineering for Business: Craft precise System and User Prompts that force AI models to deliver structured, high-value outputs suitable for strategic decision-making.

  3. Overcome the Coding Barrier (Vibe Coding): Utilize conversational AI tools to generate custom JavaScript for the Code Node, demonstrating that even custom scripting is accessible through low-code means.

  4. Integrate External Systems: Understand how to utilize AI Models within the workflow using secure API credentials.

  5. Drive Efficiency and Strategic Decisions: Immediately apply the Capstone workflow structure to map out and accelerate high-friction processes within their own functional area (examples:  Data Analysis, auto-triage support tickets, classify documents, or draft initial reports).