Core concepts
The vocabulary of Compass — every core idea, what it means, and how the pieces fit together.
This page defines the building blocks of Compass and how they relate. Read it once and the rest of the docs will click into place. Each concept links to its full guide.
Where your work lives
Organization
An organization is your company's tenancy boundary in Compass. Everything — projects, connections, agents, workflows, datasets, executions — belongs to exactly one organization, and members of one organization never see another's data.
Organizations are provisioned by Sage; members of an organization don't create them. You can belong to more than one and switch between them from the top bar.
Project
A project is a container inside an organization that holds a related set of
connections, agents, workflows, datasets, and deployments. Projects let you separate
work — for example staging from production, or one client from another.
Every organization has a Default project, and you can create more at any time. When you build in Studio, you work in one project at a time, shown in the top bar; Console looks across all of them.
→ Projects
What you connect
Connection
A connection is a saved, reusable link to an external service, with its credentials and settings stored securely. You create a connection once and reference it from anything in the project. There are three kinds:
- Provider — a model service such as Anthropic, OpenAI, or LM Studio. Each provider connection runs one model: the "brain" an agent thinks with, an embedding model a dataset indexes with, or OCR for scanned documents.
- Integration — a service or data source your AI can act on, such as Postgres, S3-compatible storage, or any API you describe with an OpenAPI spec.
- Gateway — an optional proxy (such as Apigee) that calls are routed through for monitoring and policy.
What you build
Compass has two first-class ways to build, and they're peers — you can use either, or combine them.
Agent
An agent is a single AI worker. You give it written instructions, choose a model (a provider connection), and attach the tools it's allowed to use. At runtime it reads its input, reasons, calls tools as needed, and produces a result — either free-form text or a structured object you define. An agent's harness decides what Compass adds around it: none, or the Compass harness, which lets it work with Compass itself.
Workflow
A workflow is a graph of steps you assemble visually on the canvas. Each step is a node; you wire nodes together so the output of one feeds the input of the next. Workflows are the right tool when you want explicit, multi-step logic — fetch data, run an agent, transform the result, call an API — laid out as a diagram.
Node
A node is a single step on the canvas. The main node types are:
- Input and Output — the workflow's entry point and its result.
- Agent — an AI step (the same agent concept, embedded in a workflow).
- Prompt — renders a text template with values from earlier steps.
- Workflow — runs another workflow as a step.
- Embeddings — turns text into vectors with an embedding model.
- Components — deterministic steps for documents and data: the Document Splitter, Document Parser, and Dataset.
- Integration — calls a connected service.
Tool
A tool is a capability you grant an agent so it can act, not just talk. A tool can be an integration's actions (e.g. "query the customers table"), an entire workflow, another agent, or a component such as a dataset search. The agent decides when to call its tools while it works; every call is recorded in the execution's trace.
Dataset
A dataset is a searchable collection of your documents. Upload files or sync a folder from storage, and Compass reads, splits, and indexes them so agents, workflows, and Compass Chat can search them by meaning and answer from your own material.
→ Datasets
How you run it
Version
When you deploy, Compass freezes the current draft into an immutable, numbered version (v1, v2, …). Versions never change, so an execution can always be traced back to the exact definition that produced it.
Deployment
A deployment is the live binding of an agent or workflow to one version, plus the connections it runs on and any schedules attached to it. Think of it as a movable pointer: you promote a version to make it live, roll back to an earlier one at any time, and point it at different connections without redeploying.
Trigger
A trigger is what starts an execution. Today you can run from Compass Chat, on a schedule (a cron-style timetable), or through the API. Webhook and event triggers are on the way.
Compass Chat
Compass Chat is the conversational way into Compass. Hand it your agents, workflows, integrations, and datasets as tools and ask it to do the work; ask it what ran and why; have it draft new workflows and agents for your approval. Replies stream in real time, and every turn has a trace.
What you observe
Execution
An execution is one dispatch of an agent or workflow. It records the input, the output (or error), how long it took, the tokens it used and what they cost, what triggered it, and which version ran. Executions are the heart of Observability.
Trace
A trace is the step-by-step record inside an execution: every node that ran, every tool the agent called, the inputs and outputs at each step, and any child executions. While an execution is in progress you can watch it stream live; after it finishes you can explore the whole tree. The trace is how you understand and debug what your AI actually did.