The vocabulary the exams and the daily work both assume you already have. Every entry gives the definition, the source it is drawn from, and the misreadings that follow from getting it wrong.
265 concepts, page 6 of 14
Why a change to a baseline is a decision, the path a change request takes from submission to a reissued baseline, who may approve one and how the same problem appears on adaptive work.
Project Management
What the field has established about the inside of a model, what it has not, and why a system that explains itself is not explaining itself.
Artificial Intelligence
Risks, assumptions, issues and dependencies in one place, why the boundary between a risk and an issue is the one that matters, and what keeps a log usable.
Project Management
A fixed cadence, a variable scope and a usable result at the end of every cycle, together with the events that make the loop work and the reason each of them is timeboxed.
Project Management
Visualisation of the work, a limit on how much is started at once, and management of the queues between stages, which together control delivery where a fixed cycle does not suit the work.
Project Management
Running the work and leading the people are two jobs held by one person. The leadership style that works is the one the competence and confidence of each team member require for the task in hand.
Project Management
Connect early signals to customer and business outcomes, define metric denominators and time lags, and avoid treating correlation as proof.
Strategy
Why lessons are captured continuously, the difference between a project register and an organisational repository, and what makes a lesson reusable.
Project Management
Secure LLM applications with access controls, output validation, scoped tools and approval checks. Test what happens when model instructions fail.
Artificial Intelligence
Understand context rot, lost in the middle effects, conflicting evidence and polluted agent memory, with practical tests for long context reliability.
Artificial Intelligence
Understand LLM context window limits and build a token budget for instructions, retrieved documents, history, tool results and generated output.
Artificial Intelligence
Complete a practical LLM capstone with prompts, retrieval, validated outputs, controlled tools, evaluation evidence and a rehearsed release decision.
Artificial Intelligence
Build representative LLM evaluation datasets from real and designed cases, prevent leakage and interpret small sample results with appropriate uncertainty.
Artificial Intelligence
Learn how LLM function calling works and design tool names, schemas, permissions and results that an application can validate before execution.
Artificial Intelligence
Learn how LLM grounding connects answers to evidence, how it differs from RAG and how to check citations, source quality and unsupported claims.
Artificial Intelligence
Plan an LLM model migration with API compatibility checks, controlled evaluations, prompt adaptation, canary rollout and a viable fallback.
Artificial Intelligence
Trace LLM requests across retrieval, model calls, validation and tools. Learn what to record, how to protect data and where replay stops being reproducible.
Artificial Intelligence
Monitor LLM applications for answer quality, retrieval failures, tool errors and drift, with meaningful samples, denominators and actionable alerts.
Artificial Intelligence
Learn when to split an LLM task into a prompt chain, how to validate intermediate steps and how dependencies affect reliability, cost and latency.
Artificial Intelligence
Choose effective system prompts, role prompts, decomposition and self consistency techniques, with examples and clear limits for each pattern.
Artificial Intelligence