AIDLC Glossary

Terms, A to Z

Agent

An AI system that takes a goal and executes multiple steps to reach it: planning, editing files, running commands, and checking results before handing back work for review. Unlike an assistant, it acts rather than answers.

Agentic coding

Delegating a scoped engineering task to an AI agent that plans the work, edits across multiple files, runs commands, and returns a diff. The developer defines the task and reviews the result; the agent does the mechanical execution.

AIDLC

The AI Development Life Cycle: a five-phase framework - Analyze, Ideate, Develop, Launch, Curate - that integrates AI into every stage of software delivery, replacing the human-only assumptions of traditional SDLC.

Assistant

An AI system that responds to a single prompt with a single answer. It waits for instruction and does not act on its own. The chat interface most developers started with.

Context engineering

The practice of giving an agent everything it needs to do a task well: clear intent, acceptance criteria, the relevant code and docs, constraints, guardrails, and a feedback loop it can run. It is the upstream work that determines whether output is production-ready or throwaway.

Context window

The maximum amount of text a model can consider at once, measured in tokens. Everything the model knows about your task in a given exchange has to fit inside it.

Diff review

Reading and judging the specific changes an agent proposes before accepting them. In AIDLC this is the non-negotiable human checkpoint of the Develop phase.

Grounding

Anchoring a model's output in real, retrievable source material - your code, your docs, your data - rather than letting it rely on training-time recall.

Guardrails

The constraints placed around an agent's work: what it may edit, which commands it may run, which checks must pass, and what requires human approval before it proceeds.

Hallucination

Output that is fluent and confident but wrong - an invented API, a misremembered flag, a citation that does not exist. It is the reason review and grounding are structural rather than optional.

Harness

The tool an agent runs inside: the IDE, CLI, or platform that gives it file access, command execution, and a review surface. The same model can behave quite differently across harnesses.

Invariant

A property that must always hold true, declared up front so it can be checked automatically. Verifying by invariant asks whether a rule survives many generated cases, not whether one example happened to pass.

MCP (Model Context Protocol)

A standard way for models and agents to connect to tools, data, and systems. It replaces brittle one-off integrations with a governed interface to your docs, tickets, databases, and services.

Multi-agent workflow

Several agents working on different parts of a problem, in parallel or in sequence, with their output merged and reviewed. It pays off when the tasks are genuinely independent.

Orchestration

Coordinating multiple agents, steps, or tools into a repeatable process: how work is split, how state is passed along, and where a human steps in.

Prompt

The instruction given to a model or agent. In AIDLC a prompt is an input to a specification, not a substitute for one.

SDLC

The Software Development Life Cycle: the traditional model of building software in defined phases, designed in an era when every phase was carried out exclusively by humans.

Spec-driven development

Writing a clear specification first, having an agent plan and execute against it, then reviewing the result against that spec. It is the disciplined alternative to prompting loosely and hoping.

Token

The unit models read and write, roughly a fragment of a word. Context windows, pricing, and rate limits are all measured in tokens.

Vibe coding

Prompting loosely and accepting whatever an agent produces without meaningful review. It ships quickly and accrues debt invisibly, and guarding against it is much of why AIDLC exists.