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.
Course Outline
Module 1: Introduction & AI Theory
- The Model-Based Approach: Treating AI as an engineering challenge.
- Demystifying the "Ghost in the Machine": Distinguishing what AI is from what it is not.
- Technological Evolution: Progression from BERT to Transformers.
- Generative Domains: Analysis, Creative writing, Research, Image, Music, and Video.
- Data Governance: Core pillars, audits, and current trends (Multimodality, Agents, RAG, LLM vs. SLM).
- Ethical Considerations: IP rights, bias, hallucinations, and social engineering risks.
- Risk Assessment: Data poisoning, Nepenthes, and the potential for "dumbing down" human capabilities.
- Model Taxonomy: Foundation vs. Task-specific; Closed vs. Open-weight models.
Module 2: Current Landscape & Toolset
- The Language Models Arena: Comparing performance metrics and benchmarks.
- Criteria for Professional Adoption: Cost, latency, privacy, and vendor lock-in.
- Overview of Major Models: OpenAI ChatGPT, Perplexity, Gemini, and Grok.
- Specialized & Smaller Models: Manus, SpecKit.
- Graphical Generation: Perchance
- Technical Limitations: Context rot vs. Token cost.
Module 3: Interaction - Prompt & Context Engineering
- Verification Framework: Ensuring completeness, consistency, and verifiability.
- RAG Strategy: Determining when to employ Retrieval-Augmented Generation versus fine-tuning.
- AI Return on Investment: Balancing maintenance costs against productivity improvements.
- Advanced Techniques: Over 20 Prompt & RAG methods with practical examples.
- Experimental Frontiers: Triangulation, Map & Terrain overview, and Model-based generation.
Module 4: AI in Agile Project Management
- The Supercomputer Pilot: Utilizing AI as an automation engine.
- Decision Making: Balancing human responsibility with AI assistance.
- AIOps & GitOps: Incorporating AI into operational workflows.
- Toolchains & Pipelines: Establishing a seamless AI-driven environment.
- Agile Artifacts: Managing Backlog, roadmaps, and requirements engineering.
- Precision Management: Capacity planning and estimation (distinguishing Accuracy from Precision).
- Product Ownership: Ideation, feature analysis, and risks associated with Vibe-coding.
- Risk & Scenarios: Planning for contingencies and automated risk management.
- Refinement: Describing and refining Use Cases and User Stories.
Requirements
- Foundational knowledge of the Agile Manifesto and Scrum framework.
- Background in project management, product ownership, or team leadership.
- No prior experience in programming or AI engineering is necessary, although general familiarity with digital tools is advised.
Target Audience
- Agile Project Managers and Scrum Masters.
- Product Owners and Product Managers.
- IT Team Leaders and Delivery Managers.
- Business Analysts operating within Agile environments.
- Operations Managers interested in AIOps.
7 Hours
Testimonials (1)
Understand AI function n tools to make our job easier. Need to improved AI Chubb such as make analysis n creating presentation
