AI Training Matrix

Understanding Generative AI: LLMs, GPT-4, Claude, Gemini explained simply • How AI creates text, images, code — and what that means for business • Agentic AI: autonomous agents, tool use, real-world business impact • Key AI use cases across industries: Healthcare IT, BFSI, Retail, Tech • Strategic AI adoption framework — build vs. buy vs. augment • Risk management: hallucinations, bias, IP concerns, governance • Competitive landscape: OpenAI, Anthropic, Google, Microsoft, Meta • Creating your personal AI strategy and 90-day adoption roadmap

Introduction to GenAI and how it applies to software testing • Using ChatGPT and Copilot to generate test cases from requirements • AI-assisted test data generation and masking • Prompt templates for BDD/Gherkin test scenarios • Defect triage and root cause analysis with AI • Exploratory testing support: idea generation & heuristics • AI limitations and how to validate AI-generated tests • Integrating AI tools into your existing QA workflow

How LLMs work: tokens, attention, temperature, and context windows • Zero-shot, few-shot, and chain-of-thought prompting techniques • Role prompting and persona assignment for better outputs • Writing prompts for user stories, acceptance criteria, retrospectives • Using Claude, ChatGPT, and Gemini for agile ceremonies • Prompt debugging: why prompts fail and how to fix them • Building prompt templates for reusable agile workflows • Safety, ethical use, and responsible prompting

Setting up ChatGPT for BA workflows with custom instructions • AI-assisted requirements gathering from stakeholder interviews • Writing user stories, acceptance criteria, and use cases with AI • Generating process documentation and workflow diagrams • Gap analysis and impact assessment automation • AI-powered stakeholder communication templates • Data analysis narration and insight generation • Ethical guidelines and bias awareness for BAs using AI

Vibe Coding techniques: zero-shot, few-shot, chain-of-thought • Structuring prompts for reliable code generation • Introduction to RAG (Retrieval-Augmented Generation) • How vector embeddings work: semantic search fundamentals • Building a simple Q&A app over documents with RAG • OpenAI API and Anthropic API: first steps • Prompt injection risks and how to defend against them • Best practices for AI-assisted software development

Core principles of effective prompting for non-technical roles • Using AI for emails, reports, meeting summaries, and presentations • Crafting prompts for research, analysis, and decision support • AI for HR: job descriptions, interview questions, onboarding content • AI for Finance: financial summaries, variance narratives • Privacy and confidentiality: what NOT to share with AI tools • Building a personal AI productivity toolkit • Getting started with Microsoft Copilot and ChatGPT at work

AI-driven project scoping: WBS generation and effort estimation • Risk identification, risk register automation with GenAI • Automated status reports, executive summaries, and stakeholder updates • Meeting transcription, action-item extraction, and follow-up generation • Resource allocation optimization using AI recommendations • RAID log management with AI assistance • Integrating AI into PMO tools (Jira, MS Project, Smartsheet) • Measuring AI productivity gains in PM workflows

Automated test case generation from user stories and PRDs • BDD/Gherkin scenario generation with AI for Given-When-Then • API test generation using Postman + AI integration • Regression suite optimization: reducing redundancy with AI • AI-powered exploratory testing: session planning and heuristics • Test coverage analysis and gap detection using LLMs • Mutation testing concepts with AI assistance • Creating AI-enhanced test reporting and dashboards

AI-assisted Sprint Planning: story point estimation and velocity prediction • Automated Daily Standup summaries and blocker identification • AI for Sprint Review: demo preparation and stakeholder briefings • Retrospective facilitation: theme identification and action items • Backlog refinement: story splitting, acceptance criteria generation • Using AI for impediment resolution and dependency mapping • Capacity planning and team performance analytics with AI • Building AI-powered agile dashboards and reports

Machine Learning fundamentals: supervised, unsupervised, reinforcement learning • Deep Learning concepts: neural networks, CNNs, RNNs, and transformers • AI transformation roadmaps: from pilot to enterprise scale • Building AI-first culture: change management and upskilling strategies • AI governance frameworks: responsible AI, ethics, and compliance • Measuring AI ROI: KPIs, productivity metrics, and value quantification • Vendor evaluation and AI platform selection (make vs. buy analysis) • Industry-specific AI applications: Healthcare IT, BFSI, Retail use cases

AI Agents for end-to-end test automation: architecture and design patterns • Playwright + AI: generating, maintaining, and self-healing test scripts • Selenium with GitHub Copilot: intelligent test generation and refactoring • Self-healing frameworks: DOM change detection and auto-correction • Visual AI testing: screenshot comparison and visual regression • CI/CD integration: GitHub Actions, Jenkins with AI-powered test gates • Performance and load testing with AI scenario generation • Building autonomous testing agents using LangChain and OpenAI

PSPO I & II (Professional Scrum Product Owner) exam preparation • PSM I & II (Professional Scrum Master) certification deep dive • AI-powered product roadmap generation and prioritisation • OKR frameworks with AI-assisted goal setting and tracking • Using AI for market research, personas, and journey mapping • Advanced backlog management: Epic decomposition with AI • AI-enhanced stakeholder management and negotiation support • Scaling Scrum with AI: SAFe and LeSS with AI integration

AI Agent architecture: ReAct, Plan-and-Execute, and Reflexion patterns • OpenAI Agents SDK: building, testing, and deploying agents • Anthropic Claude API: tool use, computer use, and multi-turn conversations • Google Gemini API: multi-modal agents and function calling • Model Context Protocol (MCP): building MCP servers and clients • Multi-agent orchestration: CrewAI, LangGraph, AutoGen frameworks • Agentic RAG: dynamic retrieval, re-ranking, and memory systems • Voice agents, multi-modal AI, and real-world agent deployment

• AI for Project Management: Real-World AI Use Cases (4.5 hrs) • Prompt Engineering Certification (2.5 hrs) • Microsoft Copilot for PMs (2 hrs) • AI Business Strategy for Leaders (7.5 hrs)

• Generative AI for QA Professionals (4 hrs) • Master Generative AI for Testing (11.5 hrs)

Advanced certification preparation for Product Owners and Scrum Masters with AI integration - Click to browse all related courses

• Generative AI for Business Professionals (3 hrs) • ChatGPT & AI for Data Analysis (5 hrs) • Prompt Engineering for Data & Analytics (4 hrs) • AI for BI & Analytics (8 hrs) • GenAI for Process Improvement (5 hrs)

• The AI Engineer Course 2026 (29.5 hrs) • LangChain - Agentic AI Engineering (19 hrs) • 2026 Bootcamp: GenAI, LLM Apps (11.5 hrs) • Agentic AI Architectures with MCP (6.5 hrs)

Introduction to AI fundamentals and Claude AI basics for software engineers.

Learn Model Context Protocol fundamentals, advanced API integration, and practical coding with Claude AI.

Master the Model Context Protocol for advanced AI system integration and earn the Claude Certified Architect credential.