Glossary

The agentic AI glossary.

The vocabulary of agent systems, defined in plain language — and what each concept looks like inside a working runtime.

All terms

AI agent

An AI system that pursues a goal by taking actions — calling tools, reading data, making decisions — rather than only generating text.

Read →

Agentic workflow

A workflow where one or more steps are performed by a reasoning agent instead of fixed logic.

Read →

Autonomous agent

An agent that operates without step-by-step supervision: given an objective, it plans, acts, evaluates its own results and continues until done or blocked.

Read →

Multi-agent system

Multiple agents cooperating on work too broad for one — a researcher feeding a writer feeding a reviewer, or specialists coordinated by an orchestrator.

Read →

Agent orchestration

Coordinating which agent or tool acts, in what order, with what context — routing tasks, merging results, retrying failures and enforcing gates.

Read →

Agent memory

Persistent state an agent carries across sessions: facts about its user, corrections received, patterns that worked.

Read →

Agent skills

Packaged, versioned expertise an agent loads on demand — a playbook containing process, standards and examples for one class of task.

Read →

MCP (Model Context Protocol)

An open protocol for connecting AI models to tools and data sources through a standard interface.

Read →

MCP server

A process exposing tools, resources or prompts over the Model Context Protocol.

Read →

Tool calling

A model invoking external functions — search, database queries, file writes — by emitting structured calls its runtime executes.

Read →

Function calling

The model-side mechanism behind tool use: the model returns a structured invocation — name plus JSON arguments — matching a declared schema, which the host executes and feeds back..

Read →

LLM runtime

The environment that turns model output into real work: executing tool calls, managing context and memory, enforcing permissions, retrying failures, recording what happened.

Read →

Local-first AI

AI software whose data, credentials and execution live on hardware you control, with cloud as an option rather than a requirement.

Read →

Self-hosted AI

Running AI infrastructure — runtimes, models, or both — on your own servers.

Read →

Prompt caching

Reusing computation for the repeated prefix of prompts — system instructions, tool schemas, standing context — so consecutive calls pay only for what changed.

Read →

RAG (Retrieval-Augmented Generation)

Fetching relevant documents at query time and placing them in the model’s context, so answers ground in your data instead of training memory.

Read →

Context window

The maximum text a model attends to in one call — instructions, history, retrieved material and its own output.

Read →

Fine-tuning

Continuing a model’s training on domain examples to shift behaviour — terminology, format, tone — into the weights.

Read →

Inference

Running a trained model to produce output — the operational, per-request phase of AI, as opposed to training.

Read →

Token

The unit models read and write — roughly three-quarters of an English word.

Read →

System prompt

The standing instruction that defines a model’s role, rules and boundaries before any user input arrives.

Read →

Webhook automation

Triggering workflows from HTTP callbacks the moment events happen — a payment, a form, a commit — instead of polling on a schedule.

Read →

Human-in-the-loop

Automation that pauses for human judgment at defined points — approving an outbound email, releasing a payment, accepting a diff.

Read →

Execution receipt

A structured record an agent produces for each operation: what was read, which tools ran with what arguments, what was decided and what was written.

Read →

Give AI a job. Get the proof.