Loading…

Glossary

AI agent terminology, defined honestly.

60 terms across 7 categories. Every entry has a one-sentence definition, an engineer-grade explanation, and a link to where the concept shows up in practice.

Most glossaries read like marketing. This one is the version we wanted when we were learning the field.

Browse:Agent concepts Models & inference RAG & knowledge Runtime Cost & ops Security Ecosystem

Agent concepts

What an agent is, what's inside it, how it decides.

15 terms

The core runtime cycle of an agent: think, act, observe, repeat, until the goal is reached.

/glossary/agent-loop

The runtime mechanism that lets one agent launch another, optionally in parallel, and wait for the result.

/glossary/agent-spawn

An autonomous program that uses an LLM to plan and execute multi-step tasks via tools, in a loop, until a goal is reached.

/glossary/ai-agent

A runtime process that summarises old turns once the context window is nearly full, freeing space for new turns.

/glossary/compaction

Coordinator agent

The top-level agent in a multi-agent setup. Plans, dispatches workers, merges their results.

/glossary/coordinator

Function calling

OpenAI's term for tool use. Same concept, slightly different format.

/glossary/function-calling

A pattern where the original goal is auto-injected at the top of every turn so the LLM cannot lose the thread.

/glossary/goal-pinning

Multi-agent system

A set of agents that collaborate, typically a coordinator that spawns specialist workers in parallel.

/glossary/multi-agent

Persistent memory

State that survives across sessions, scoped per user or per agent.

/glossary/persistent-memory

Plan-first reasoning

A pattern where the agent emits a numbered plan before any tool call, then executes it step by step.

/glossary/plan-first

Read-before-edit

A safety guard that refuses to edit any file the agent has not first read, preventing hallucinated overwrites.

/glossary/read-before-edit

Specialist agent

An agent with a narrow, focused role spawned by a coordinator.

/glossary/specialist-agent

The instruction text the LLM sees before any user message. Sets the agent's role, constraints, and behaviour.

/glossary/system-prompt

The LLM capability to emit a structured call to an external function, which the runtime executes and feeds back as context.

/glossary/tool-use

Per-session state the agent can write and read across turns, including a goal, a todo list, and arbitrary key-value notes.

/glossary/working-memory

Models & inference

LLMs, tokens, context, the math layer underneath.

9 terms

The maximum number of tokens an LLM can process in a single call. Modern frontier models offer 200K to 2M.

/glossary/context-window

The highest-quality, most expensive tier from a provider. Claude Sonnet, GPT-4o, Gemini Pro.

/glossary/frontier-model

The act of running a trained model to produce output. The thing you pay for per token.

/glossary/inference

A neural network trained on text that takes a prompt and returns text, optionally including structured tool calls.

/glossary/llm

Open-weight model

A model whose weights are publicly downloadable, runnable on your own hardware via Ollama, vLLM, or similar.

/glossary/open-weight-model

Receiving the LLM's output token-by-token as it generates, instead of waiting for the full response.

/glossary/streaming

A 0-to-1 dial that controls how random the model's output is. Lower = more deterministic.

/glossary/temperature

The units LLMs process. Roughly four characters of English per token, billed per million.

/glossary/tokens

The JSON shape a provider expects for tool definitions and tool calls. Differs slightly per provider.

/glossary/tool-format

RAG & knowledge

Retrieval, embeddings, the patterns for grounding answers.

8 terms

Splitting source documents into smaller pieces (paragraphs, sections) before embedding them for retrieval.

/glossary/chunking

A fixed-size numeric vector that represents the semantic meaning of a piece of text.

/glossary/embedding

Combining vector similarity with keyword matching to get the best of both.

/glossary/hybrid-search

The collection of documents an agent retrieves from. The 'data' side of RAG.

/glossary/knowledge-base

A pattern where relevant documents are fetched from a knowledge base and pasted into context before the LLM answers.

/glossary/rag

Re-ordering retrieved candidates with a more expensive model to put the best matches at the top.

/glossary/rerank

Semantic search

Searching by meaning instead of keywords. Powered by embeddings and vector databases.

/glossary/semantic-search

Vector database

A database optimised for storing and querying high-dimensional vectors, typically for similarity search.

/glossary/vector-database

Runtime

Hooks, hot reload, triggers, the plumbing that makes agents shippable.

10 terms

Behaviour rules

Focused guards that protect against common agent failure modes (runaway loops, repeated tool calls, drift).

/glossary/behavior-rules

A trigger that fires an agent on a cron schedule.

/glossary/cron-trigger

Filesystem module

The runtime module that exposes file operations (read, write, edit, grep, glob) to the agent.

/glossary/filesystem-module

Declarative event handlers that fire at specific points in an agent's lifecycle (turn_start, tool_end, etc).

/glossary/hooks

Re-applying config changes to a running agent in place, without restarting the process.

/glossary/hot-reload

A bundle of tools the agent can call (filesystem, web, shell, channels). Declared in YAML, loaded at boot.

/glossary/module

Declarative entry points that launch an agent on an event: cron, webhook, file watch, or message.

/glossary/triggers

Webhook trigger

A trigger that exposes an HTTP endpoint, fires the agent when something POSTs to it.

/glossary/webhook-trigger

The runtime module that mirrors the agent's writes to a live preview (React, LaTeX, slides, code, markdown).

/glossary/workspace

YAML-first config

Defining agents declaratively in a YAML file the runtime executes, instead of imperatively in framework code.

/glossary/yaml-first

Cost & ops

Routing, caps, compaction, audit logs.

7 terms

A structured record of every agent turn, including tool calls, costs, and outputs, written to a sink.

/glossary/audit-log

A second LLM provider the runtime swaps to when the primary returns an error or runs out of credit.

/glossary/brain-fallback

A hook that stops the agent when its session has exceeded a configured cost ceiling.

/glossary/cost-cap

Sending different turn types to different models (cheap for exploration, premium for writing).

/glossary/model-routing

Pattern-matching personal data in tool results and replacing it before the LLM sees it.

/glossary/pii-redaction

Capping a tool to N calls per minute, per session, or per user, to protect downstream APIs.

/glossary/rate-limiting

A runtime ceiling on how many loop iterations an agent can take before the runtime forces it to stop.

/glossary/turn-cap

Security

Credentials, scopes, encryption, the don't-leak-keys layer.

5 terms

Credential vault

An encrypted store for API keys, tokens, and connection strings, referenced from YAML by name.

/glossary/credential-vault

Envelope encryption

An encryption scheme where each row has its own data key, and that data key is wrapped by a master key.

/glossary/envelope-encryption

A managed service that holds master keys and performs cryptographic operations, never exposing the keys.

/glossary/kms

A multi-step authentication flow where the user grants the agent scoped access to a third-party service.

/glossary/oauth-flow

A credential resolution mode where each user brings their own key, resolved at session start.

/glossary/per-user-scope

Ecosystem

Frameworks, marketplaces, the wider field.

6 terms

Agent framework

Software that handles the agent loop, tool registration, and orchestration, so you do not write it yourself.

/glossary/agent-framework

Agent marketplace

A registry where agents can be published, discovered, and installed by name (like a package manager for YAML).

/glossary/agent-marketplace

Adjective describing software that uses LLMs in a goal-directed loop with tools, instead of one-shot.

/glossary/agentic

A Python multi-agent framework that organises agents into role-based crews.

/glossary/crewai

The most widely used Python framework for building LLM agents. Class-based, code-first.

/glossary/langchain

Running your agent stack on infrastructure you control, with your own model provider keys.

/glossary/self-hosting