DURGA SOFTWARE SOLUTIONS

Courses Offered:

SCJP SCWCD Design patterns EJB CORE JAVA AJAX Adv. Java XML STRUTS Web services SPRING HIBERNATE

Master AI Testing & AI Quality Engineering Course Details
Subcribe and Access : 5200+ FREE Videos and 21+ Subjects Like CRT, SoftSkills, JAVA, Hadoop, Microsoft .NET, Testing Tools etc.. Batch Date: July 20th @9:00AM Faculty: Mr. Vishwa (12+ Yrs Of Exp,..) Duration: 3 Months Venue : DURGA SOFTWARE SOLUTIONS, Flat No : 202, 2nd Floor, HUDA Maitrivanam, Ameerpet, Hyderabad - 500038 Ph.No: +91 - 8885252627, 9246212143, 80 96 96 96 96 Syllabus: Master AI Testing & AI Quality Engineering LLM Testing \| RAG Evaluation \| AI Agent Testing \| Agentic AI Testing \| MCP Testing \| AI Test Automation \| AI Security Build AI Systems → Test AI → Evaluate AI → Automate AI Testing → Secure AI MODULE 1 — SOFTWARE TESTING TO AI QUALITY ENGINEERING Days 1–3 Topics Introduction to Software Testing Why Software Testing is Required Manual Testing Automation Testing AI-Assisted Testing Using AI for Automation Testing AI-Driven Testing AI-Driven Test Automation AI Testing AI Test Automation AI Quality Engineering Traditional Software vs AI Applications Deterministic vs Probabilistic Systems Expected Result vs AI Evaluation Why Traditional Assertions Are Not Enough for AI Role of an AI Quality Engineer AI Testing Career Opportunities Hands-On Compare manual and automation testing Create traditional test scenarios Compare traditional application testing with AI application testing Create the first AI testing checklist MODULE 2 — AI, GENERATIVE AI & LLMFOUNDATIONS Days 4–7 Topics Artificial Intelligence Machine Learning Deep Learning Neural Networks RNN LSTM Attention Transformer Architecture Foundation Models Generative AI Large Language Models — LLM Small Language Models — SLM Vision Language Models — VLM Multimodal Models Diffusion Models Embedding Models Reranker Models Tokens Tokenization Context Window Parameters Inference Temperature Top-P System Prompt User Prompt Assistant Response Hallucination Model Non-Determinism Hands-On Call an LLM API using Python Change temperature and compare responses Analyse token usage Test the same prompt multiple times Compare deterministic software output with LLM output Mini Project Build a basic VishwaTech AI Assistant MODULE 3 — PYTHON & PYTEST FOR AI TESTING Days 8–12 Topics Python Environment Setup VS Code Setup Python Variables Data Types Lists Tuples Dictionaries Sets Conditions Loops Functions Modules Packages Classes and Objects Exception Handling JSON Handling File Handling Environment Variables REST API Calls Logging Introduction to pytest Test Functions Assertions Fixtures Parameterized Testing Markers Test Data Management pytest Reports Hands-On Create Python AI API client Read prompts from JSON and CSV Execute multiple AI test cases Create pytest test suites Create parameterized AI tests Generate test reports MODULE 4 — BUILDING & TESTING LLMAPPLICATIONS Days 13–18 Build VishwaTech Cybersecurity AI Assistant Application Architecture User ↓ 5 Python Application ↓ Prompt ↓ LLM API ↓ Response Topics LLM Application Architecture Prompt Design System Prompts Prompt Templates LLM Parameters Response Handling Structured Outputs JSON Outputs Model Errors Rate Limits Timeouts Retries LLM Testing Topics Functional Testing of LLM Applications Prompt Testing Answer Relevance Answer Correctness Response Consistency Hallucination Testing Faithfulness Toxicity Testing Bias Testing PII Leakage Testing System Prompt Leakage Refusal Testing Boundary Testing Negative Testing Multilingual Testing Tools Python pytest OpenAI or Azure OpenAI DeepEval promptfoo Hands-On Create 100-prompt test dataset Run automated LLM tests Create evaluation metrics Configure quality thresholds Generate PASS/FAIL results Project 1 Automated LLM Quality Evaluation Framework MODULE 5 — EMBEDDINGS, VECTOR DATABASES& RETRIEVAL TESTING Days 19–12 Topics What Are Embeddings Text to Vector Conversion Vector Dimensions Semantic Similarity Cosine Similarity Euclidean Distance Vector Search Keyword Search vs Semantic Search Vector Databases Document Loading Document Chunking Chunk Size Chunk Overlap Metadata Top-K Retrieval Similarity Scores Reranking Tools Chroma or Qdrant Python Embedding Models Testing Topics Embedding Quality Testing Semantic Similarity Testing Chunking Validation Metadata Validation Vector Search Testing Top-K Testing Retrieval Ranking Testing Reranker Testing Duplicate Document Testing Hands-On Create embeddings Store vectors Perform semantic search Inject bad chunks Create duplicate documents Test retrieval quality MODULE 6 — BUILDING & TESTING RAGAPPLICATIONS Days 23–30 Build VishwaTech Employee Policy RAG Assistant Architecture PDF Documents ↓ Document Loader ↓ Chunking ↓ Embedding Model ↓ Vector Database ↓ Retriever ↓ Context ↓ LLM ↓ Answer Topics What Is RAG Why RAG Is Required RAG Architecture Indexing Pipeline Retrieval Pipeline Generation Pipeline Naive RAG Advanced RAG Concepts Hybrid Search Reranking Query Transformation RAG Testing Document Ingestion Testing Chunk Testing Embedding Testing Vector Database Testing Retrieval Testing Context Testing Generation Testing End-to-End RAG Testing Context Precision Context Recall Answer Relevance Faithfulness Groundedness Retrieval Accuracy Hit Rate MRR NDCG Hallucination in RAG Stale Document Testing Missing Document Testing Conflicting Document Testing RAG Regression Testing Tools LangChain Chroma or Qdrant Ragas DeepEval Hands-On Build RAG application Create golden dataset Inject retrieval defects Automate RAG evaluation Compare chunk sizes Compare Top-K configurations Generate RAG quality report Project 2 Enterprise RAG Testing & Evaluation Platform MODULE 7 — BUILDING AI AGENTS Days 31–35 Build VishwaTech IT Support AI Agent Agent Tools get_user check_account unlock_account reset_password create_ticket check_ticket send_notification Topics What Is an AI Agent LLM vs AI Agent Agent Architecture Tools Tool Calling Function Calling Agent State Memory Short-Term Memory Long-Term Memory Planning Reasoning Workflows Observation Action Agent Loop Single Agent Systems Tools LangChain LangGraph Python Hands-On Create agent tools Create tool schemas Build an AI agent Add memory Add tool calling Create multi-step tasks MODULE 8 — AI AGENT TESTING Days 36–40 Topics Agent Functional Testing Agent Behaviour Testing Tool Selection Testing Tool Calling Testing Tool Argument Validation Tool Sequence Testing Planning Testing Task Completion Testing Agent Loop Detection Retry Testing Timeout Testing Memory Testing Memory Contamination Context Contamination Unauthorized Action Testing Human Approval Testing Agent Reliability Testing Agent Regression Testing Automated Metrics Tool Selection Accuracy Tool Argument Accuracy Task Completion Rate Goal Completion Rate Tool Call Count Agent Loop Rate Retry Rate Agent Failure Rate Hands-On Create 100 agent test scenarios Inject wrong tool selection Inject invalid tool parameters Create agent loops Test memory contamination Automate agent evaluation Project 3 AI Agent Automated Testing Framework MODULE 9 — AGENTIC AI & AGENTIC WORKFLOWTESTING Days 41–45 Build AI Cybersecurity Incident Response Agent Workflow Security Alert ↓ Analyse Alert ↓ Check User ↓ Check IP Address ↓ Check Logs ↓ Calculate Risk ↓ Create Incident ↓ Request Human Approval ↓ Disable Account ↓ Generate Incident Report Topics AI Agent vs Agentic AI Goal-Based AI Systems Planning Dynamic Decision Making Replanning Multi-Step Workflows State Management Human-in-the-Loop Multi-Agent Introduction Agent Orchestration Testing Topics Planning Accuracy Workflow Testing Decision Path Testing Step Sequence Validation Replanning Testing Goal Completion Testing Human Approval Boundary Testing Excessive Agency Testing Multi-Step Failure Testing Partial Completion Testing Recovery Testing Agentic Workflow Regression Testing Hands-On Create Agentic AI workflow Inject failed tools Test replanning Test incorrect decision paths Test human approval bypass Automate workflow validation Project 4 Agentic AI Security Incident Response Testing Platform MODULE 10 — MCP FOUNDATIONS & MCPSERVER DEVELOPMENT Days 46–49 Build VishwaTech Security MCP Server MCP Tools get_alert get_user check_ip get_logs create_incident disable_user Topics What Is MCP Why MCP Is Required MCP Architecture MCP Host MCP Client MCP Server Tools Resources Prompts Tool Schemas Input Schemas MCP Communication MCP Transport Concepts MCP Server Lifecycle MCP Inspector Hands-On Create MCP server Create MCP tools Expose resources Test tool discovery Invoke MCP tools Debug using MCP Inspector MODULE 11 — MCP TESTING & MCP SECURITYTESTING Days 50–53 Topics MCP Functional Testing MCP Server Testing Tool Discovery Testing Tool Schema Testing Input Validation Invalid Arguments Missing Arguments Wrong Data Types Tool Error Handling Tool Timeout Testing Authentication Testing Authorization Testing Permission Testing Unauthorized Tool Access Sensitive Data Exposure Tool Abuse Tool Manipulation Malicious Tool Responses Tool Poisoning Concepts MCP Security Testing Tools MCP Inspector pytest promptfoo Python Hands-On Automate MCP tool tests Send malformed tool arguments Test unauthorized tool access Test sensitive data exposure Inject malicious tool responses Generate MCP security test report Project 5 MCP Automated Testing & Security Validation Framework MODULE 12 — AI SECURITY & RED TEAM TESTING Days 54–56 Topics AI Threat Landscape OWASP GenAI Security Risks Prompt Injection Indirect Prompt Injection Jailbreak Testing System Prompt Leakage Sensitive Information Disclosure PII Leakage Insecure Output Handling Excessive Agency Model Denial of Service Concepts RAG Poisoning Knowledge Base Poisoning Vector Database Poisoning Memory Poisoning Agent Tool Abuse MCP Tool Manipulation Adversarial Prompt Testing AI Red Teaming Tools promptfoo OWASP GenAI Security Project Python pytest Hands-On Create attack prompt dataset Execute automated red team tests Calculate attack success rate Test prompt injection resistance Test data leakage Test excessive agency Generate AI security report MODULE 13 — AI TEST AUTOMATIONFRAMEWORK Days 57–58 Architecture Test Dataset ↓ pytest Test Orchestrator ↓ LLM Tests RAG Tests Agent Tests MCP Tests Security Tests ↓ Evaluators ↓ DeepEval Ragas promptfoo ↓ Quality Scores ↓ Thresholds ↓ PASS / FAIL Topics AI Test Framework Architecture Reusable Test Libraries Evaluator Design Dataset Management Golden Dataset Synthetic Test Data Regression Dataset Test Configuration Threshold Management Model Comparison Prompt Version Comparison Evaluation Reports Quality Gates Hands-On Build unified AI test framework Execute complete AI regression suite Compare two prompts Compare two models Create quality thresholds Generate consolidated report MODULE 14 — DOCKER, CI/CD & AI QUALITYGATES Days 59 Topics Docker Fundamentals Dockerfile Containerising AI Tests Environment Variables Secret Management Basics Git Fundamentals GitHub Repository CI/CD Concepts GitHub Actions AI Test Pipeline Quality Gates Deployment Blocking Scheduled AI Evaluations Regression Testing Pipeline Developer Push ↓ GitHub Actions ↓ LLM Tests ↓ RAG Tests ↓ Agent Tests ↓ MCP Tests ↓ AI Security Tests ↓ Evaluation Report ↓ Quality Gate ↓ PASS → Deploy FAIL → Block Deployment Hands-On Containerise AI testing framework Create GitHub Actions pipeline Run AI tests in CI/CD Configure threshold-based quality gate MODULE 15 — CAPSTONE, INTERVIEW & CAREERPREPARATION Days 60 Capstone Project Enterprise AI Quality Engineering Platform Platform Must Test LLM Application RAG Application AI Agent Agentic AI Workflow MCP Server AI Security Controls Final Deliverables GitHub Repository Architecture Diagram Test Strategy AI Test Cases Golden Dataset Evaluation Metrics Automated Test Framework Security Test Report CI/CD Pipeline Quality Dashboard or Consolidated Report Interview Preparation AI Testing Interview Questions LLM Testing Scenarios RAG Testing Scenarios Agent Testing Scenarios MCP Testing Scenarios AI Security Scenarios Framework Design Questions Real-Time Production Scenarios Resume Preparation LinkedIn Profile Guidance GitHub Portfolio Guidance Mock Interview TOOLS COVERED Python pytest Playwright OpenAI / Azure OpenAI Ollama LangChain LangGraph Chroma / Qdrant DeepEval Ragas promptfoo LangSmith MCP MCP Inspector Docker Git GitHub Actions OWASP GenAI Security Project 5 REAL-TIME PROJECTS 1. Automated LLM Quality Evaluation Framework 2. Enterprise RAG Testing & Evaluation Platform 3. AI Agent Automated Testing Framework 4. Agentic AI Security Incident Response Testing Platform 5. MCP Automated Testing & Security Validation Framework CAREER ROLES AI Quality Engineer AI Testing Engineer AI Test Automation Engineer LLM Evaluation Engineer RAG Evaluation Engineer AI QA Automation Engineer GenAI Quality Engineer Agentic AI Test Engineer AI Reliability Engineer AI Security Testing Engineer Senior SDET — AI AI Quality Engineering Lead