Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 7 hours
Course Outline
Module 1: Introduction & AI Theory
- Model-Based Framework: Treating AI as an engineering discipline.
- Clarifying Capabilities: Distinguishing actual AI functions from misconceptions.
- Technological Progression: Advancements from BERT architectures to Transformer models.
- Generative Applications: Capabilities in analysis, creative output, research, imagery, audio, and video.
- Data Stewardship: Governance frameworks, audit mechanisms, and emerging trends (Multimodality, Agents, RAG, LLM vs. SLM).
- Ethical and Security Considerations: Intellectual property, bias mitigation, hallucination risks, and social engineering vulnerabilities.
- Risk Analysis: Data integrity threats, defense mechanisms, and the mitigation of cognitive skill degradation.
- Model Classification: Distinction between foundation and task-specific models; proprietary versus open-weight architectures.
Module 2: Current Landscape & Toolset
- Model Performance Benchmarks: Comparative analysis of leading language models.
- Procurement Criteria: Evaluation of cost efficiency, latency, privacy compliance, and vendor dependency.
- Large-Scale Models: Overview of OpenAI ChatGPT, Perplexity, Gemini, and Grok.
- Specialized and Lightweight Models: Examination of Manus and SpecKit.
- Visual Generation Tools: Exploration of Perchance capabilities.
- Technical Limitations: Balancing context window constraints against token expenditure.
Module 3: Interaction - Prompt & Context Engineering
- Verification Protocols: Ensuring completeness, internal consistency, and factual verifiability.
- Retrieval-Augmented Generation (RAG): Strategic application of RAG versus fine-tuning approaches.
- Return on Investment (ROI): Analyzing maintenance expenditures against productivity enhancements.
- Advanced Methodologies: Application of 20+ Prompt and RAG techniques with illustrative examples.
- Emerging Techniques: Exploration of Triangulation, Map & Terrain analysis, and Model-based generation strategies.
Module 4: AI in Agile Project Management
- Automation Integration: Deploying AI as a core engine for process automation.
- Decision-Making Protocols: Defining boundaries between human accountability and AI assistance.
- AIOps & GitOps: Embedding AI capabilities within operational workflows.
- Integrated Toolchains: Establishing seamless, AI-driven development environments.
- Agile Documentation: Managing backlogs, roadmaps, and requirements engineering processes.
- Precision Management: Optimizing capacity planning and estimation accuracy versus precision.
- Product Stewardship: Supporting ideation, feature analysis, and managing the risks associated with rapid coding practices.
- Risk Management: Scenario planning and automated mitigation of potential operational risks.
- Process Refinement: Enhancing use case definitions and user story precision.
Requirements
- Foundational understanding of the Agile Manifesto and Scrum framework.
- Professional experience in project management, product ownership, or team leadership.
- No prior programming or AI engineering experience is required, although general familiarity with digital tools is advised.
Audience
- Agile Project Managers and Scrum Masters.
- Product Owners and Product Managers.
- IT Team Leaders and Delivery Managers.
- Business Analysts operating in Agile environments.
- Operations Managers with an interest in AIOps implementation.
Testimonials (2)
correct way of prompting and including guardrails in instructions.
YEO SHI MIN - ST Engineering Aerospace Ltd
Course - ChatGPT and Microsoft 365 Copilot for Advanced Productivity
Understand AI function n tools to make our job easier. Need to improved AI Chubb such as make analysis n creating presentation
