AI Test Stack
AI Foundations for QA Professionals/Level 4B — AI Terminology & Concept Revision
Lesson

AI Jargon Handbook

A practical glossary of core AI terms with meaning, why they matter, and where QA teams use them.

6 min read
A visual glossary board showing key AI terms linked to simple definitions and QA use cases.
A visual glossary board showing key AI terms linked to simple definitions and QA use cases.

Overview

Before moving into Prompt Engineering, we need one consolidation step: a shared vocabulary. AI teams often talk in shorthand, and confusion about terms creates bad prompts, weak evaluations, and incorrect release decisions.

This lesson is your practical glossary. It is not just definition memorization. Each term is explained by meaning, usage, and QA relevance so you can apply it immediately in real test work.

A Practical Note for QA Learners

If this lesson feels more like vocabulary study than technical training, that is expected. The goal is not memorization for its own sake. The goal is to make sure that when your team says words like hallucination, context window, grounding, or RAG, everyone means the same thing.

For practical QA work, three things matter most:

  • the right term often points to the right test
  • unclear wording creates weak requirements and vague defect reports
  • shared terminology reduces miscommunication across QA, product, and engineering

Learning Goals

  • Understand the most common AI and LLM terms used in product teams.
  • Distinguish similar terms that are often confused.
  • Learn where each term appears in QA conversations and test plans.
  • Build a shared terminology baseline for manual QA and SDET teams.
  • Reduce ambiguity before starting Prompt Engineering techniques.

Core Concepts

1. The Essential AI Terminology Stack

TermMeaningTypical usage
AIBroad field for systems performing tasks that usually require human intelligenceProduct strategy, automation roadmaps
MLSubset of AI where models learn patterns from dataClassification, prediction, anomaly detection
Deep LearningML using many-layer neural networksVision, speech, LLM foundations
GenAIAI that creates new content (text, code, image, audio)Assistant features, content generation
LLMLarge language model trained to predict and generate text tokensChat assistants, summarization, coding support

Quick rule:

  • AI is the umbrella.
  • ML and DL are methods.
  • GenAI is a capability pattern.
  • LLM is one specific model family in GenAI.

2. Input and Output Terminology

TermMeaningQA implication
PromptInstruction/input to the modelPrompt quality controls output quality
TokenSmall unit of text processed by modelImpacts cost, limits, truncation
Context WindowMax tokens model can consider at onceLong input tests are required
OutputModel-generated responseMust be validated, not trusted blindly
InferenceRuntime generation processPerformance and latency testing target

Formula-level intuition:

3. Model Training and Adaptation Terms

TermMeaningUsage
PretrainingLarge-scale general training on broad corporaBase model creation
Fine-tuningAdditional training for domain/task behaviorDomain specialization
Instruction TuningTraining to follow human-style instructionsBetter assistant behavior
RLHFHuman-feedback loop for alignmentHelpfulness and safety shaping
AlignmentTechniques that make model behavior safer and more usefulPolicy and risk control

Why this matters for QA:

  • You can diagnose whether a failure is likely from base model limits, fine-tuning gaps, or prompt design.

4. Retrieval and Knowledge Terms

TermMeaningQA usage
EmbeddingVector representation of text/dataSemantic search and similarity matching
Vector DBStorage optimized for vector similarity retrievalRAG pipelines
RAGRetrieval-Augmented Generation; model uses external fetched contextReduces hallucination risk when retrieval is good
GroundingAnchoring outputs to trusted provided sourcesCitation and evidence checks

Practical warning:

  • RAG is not magic. Bad retrieval leads to bad grounded answers.

5. Output Quality and Risk Terms

TermMeaningQA handling
HallucinationPlausible but false outputFact-check and evidence checks
BiasUneven behavior across groups/languagesFairness and cohort testing
RobustnessStability under paraphrase/noise/edge inputMutation tests and regression
Deterministic vs ProbabilisticExact repeatability vs stochastic variationUse range- or rubric-based assertions
GuardrailsPolicies and controls around generationSafety test suites

6. Agent Terminology (Preview Only)

You will learn this deeply later, but you should know the words now:

TermMeaning nowNote
AgentAI workflow that can plan and act with toolsFull module later
Tool CallingModel triggering external functions/APIsFull module later
MemoryStored context across tasks/turnsFull module later
OrchestrationCoordinating multiple model/tool stepsFull module later

For this level, remember only this: an agent is not just a model answer; it is model plus execution workflow.

QA/SDET Relevance

Manual QA use:

  • Use vocabulary consistently in test charters and defect reports.
  • Separate model issues from integration issues in bug triage.
  • Ask better clarifying questions when outputs look wrong.

QA automation and SDET use:

  • Name test suites around clear concepts: context-limit tests, hallucination checks, RAG grounding checks.
  • Build reusable evaluation templates with consistent terminology.
  • Improve communication with engineering and AI platform teams.

Practical Work

Exercise: Build Your Team AI Terminology Cheat Sheet

Objective: Create one shared glossary used by QA, dev, and product.

Steps:

  1. Copy the 20 to 30 terms from this lesson.
  2. Add one project-specific example per term.
  3. Add one "what can go wrong" note per term.
  4. Review in sprint kickoff and update monthly.

Starter format:

TermOur product exampleRisk if misunderstood
Context WindowLong customer ticket + logs exceeds model limitMissing root cause detail
HallucinationModel invents API field in responseInvalid test or implementation work
RAGSupport assistant pulls policy docs before answeringWrong retrieval gives wrong answer

Reflection:

  1. Which 5 terms cause most confusion in your team today?
  2. Which misunderstood term has the highest release risk?
  3. What vocabulary must be standardized before Prompt Engineering?

Key Takeaways

  • Shared terminology is a quality control layer, not a formality.
  • Many AI failures begin as language confusion in requirements or test plans.
  • Terms like token, context window, inference, and grounding directly affect QA strategy.
  • Agent-related terms are introduced now and will be covered deeply later.
  • A team glossary reduces rework and improves cross-functional decisions.

Next Step

Continue with AI Terminology in Real QA Workflows to apply these terms in daily testing, automation, and release decisions.