CBA Certified Generative AI Practitioner

Generative Model Foundations18%

• Distinguish the pretraining, instruction-tuning and inference stages of a large language model lifecycle and what each contributes to behaviour
• Interpret the effect of sampling controls such as temperature, top-p and maximum output length on variability and reliability
• Identify how tokenisation and context window limits affect cost, truncation and the handling of long or non-English text
• Distinguish how diffusion models turn noise into images from how autoregressive models generate text token by token
• Select an appropriate model class or capability tier for a stated task, balancing quality, speed, cost and access constraints
• Recognise hallucination, knowledge cut-off effects and arithmetic weakness as predictable consequences of how models are built

Prompt Design and Iteration22%

• Select prompt components (role, context, task, constraints, output format, examples) appropriate to a stated goal
• Distinguish zero-shot, few-shot and reasoning-eliciting prompting and identify when each improves results
• Evaluate a weak prompt against a target outcome and select the revision most likely to improve the output
• Interpret an unsatisfactory response to diagnose whether the fault lies in the instructions, the supplied context or the task framing
• Apply output-format specifications, including tables, structured lists and JSON-like templates, to obtain reusable results
• Construct multi-step prompt chains that decompose a large task into ordered, checkable stages

Retrieval and Grounded Workflows15%

• Distinguish tasks that need retrieval or grounding from tasks the model can answer reliably from its training alone
• Interpret the stages of a retrieval-augmented pipeline: splitting documents into chunks, embedding, similarity search and prompt assembly
• Evaluate how chunk size, retrieval quality and stale sources affect the accuracy of grounded answers
• Select an appropriate grounding method (file upload, long-context prompting, web-connected search, retrieval pipeline) for a stated information need
• Identify citation and traceability practices that let a reader verify a grounded answer against its sources

Multimodal Creation and Editing10%

• Select image-generation prompt elements, including subject, style, composition, lighting and negative guidance, for a stated creative brief
• Distinguish the practical capabilities of text-to-image, image-to-image, vision-input, speech-to-text and text-to-speech tools
• Evaluate generated media for common artefacts and defects such as distorted text, anatomical errors and inconsistent lighting
• Interpret disclosure, provenance and licensing considerations that apply before publishing AI-generated media

Output Evaluation and Quality Control15%

• Evaluate an AI output against explicit criteria such as factual accuracy, completeness, relevance, tone and formatting
• Distinguish types of error, including fabricated facts, false citations, subtle omissions and confident wrongness, and select a suitable verification method for each
• Construct a simple rubric and small test set for a generative AI task that a team performs repeatedly
• Calculate basic quality measures, such as pass rates and error rates, from a structured spot-check recorded in a spreadsheet
• Interpret the limits of using one AI model to review another model's output

Safe Use, Data Care and Work Integration20%

• Identify categories of information, including personal data, client confidences and commercial secrets, that must not be entered into tools without appropriate safeguards
• Interpret core data protection principles, such as purpose limitation, minimisation and individual rights, as they apply to workplace generative AI use
• Distinguish consumer and enterprise tool arrangements, including training-on-your-data settings, retention and administrative controls
• Evaluate a proposed workplace use case for risk level and select proportionate human oversight and disclosure
• Recognise prompt injection, jailbreaking and data leakage risks in connected or automated workflows
• Select integration patterns that embed generative AI into everyday work, such as drafting, summarising, meeting notes and spreadsheet analysis