---
title: "Overview"
description: "How the platform builds, maintains, and surfaces your organization's knowledge."
icon: "sparkles"
---

> **For AI agents:** the complete documentation index is at [llms.txt](/llms.txt). Append `.md` to any page URL for its markdown version.

<Note>The Agentic toolset is in **beta**.</Note>

The platform maintains a single structured model of your organization's knowledge — your
**ontology** — and keeps it current as the systems and documents it describes change over
time. Two components share this model:

- The **[Ontology Agent](/agentic/ontology-agent)** builds and maintains the ontology.
- The **[Knowledge Base](/agentic/knowledge-base)** renders it as readable, portable
  documentation.

Both read from and write to the same source of truth, so your structured definitions and your
human-readable knowledge never drift apart.

## How it works

The system operates in three stages — **build**, **maintain**, and **surface** — which also
describe the lifecycle of any piece of knowledge it holds.

<Steps>
  <Step title="Build">
    The Ontology Agent reads your documents and connected data sources and instantiates the
    primitives that compose your ontology: [Thing Type Definitions](/platform/data-model#thing-type-definition),
    [Metric Definitions](/platform/data-model#metric-definition), and
    [Templates](/platform/templates). You review each proposed primitive, edit it as needed,
    and publish it.
  </Step>
  <Step title="Maintain">
    As the underlying sources change — a revised specification, a new data field, a hardware
    revision — the same agent detects the drift and proposes targeted updates to the affected
    primitives. The model stays aligned with reality instead of decaying after each change. Users can 
    also edit and maintain ontology resources and links via API, Agent, or Console.
  </Step>
  <Step title="Surface">
    On a fixed cadence, the Knowledge Base compiles the published ontology into a continuously
    maintained wiki in the [Open Knowledge Format](/agentic/knowledge-base#output-format)
    (OKF). The result is one body of knowledge in two renderings: structured primitives that
    your teams and applications build on, and open, human- and agent-readable documentation
    that anyone can consume.
  </Step>
</Steps>

The design goal is to provide the rigor of a typed ontology and the portability of an open
format at the same time, rather than trading one for the other.

## Where to start

Don't try to model everything at once. Start from the work that matters most:

- **Pick the workflow with the most leverage.** The highest-volume task, the biggest
  time-sink, or the single decision with the most leverage over revenue.
- **Define a great outcome.** Decide what success looks like for that workflow — faster,
  cheaper, or more accurate — so you can tell when you've reached it.
- **Pull in only what that outcome requires.** Connect just the data sources and integrations
  the workflow needs, not everything you have.
- **Get the highest-value capability live as soon as possible.** Ship that one workflow, prove
  the outcome, then expand from there.

<Note>Need help onboarding workflows? Reach out to our solutions group for tailored support: support@aerovy.com</Note>

## Components

<Columns cols={2}>
  <Card title="Ontology Agent" icon="wand-magic-sparkles" href="/agentic/ontology-agent">
    Generate and maintain the primitives that model your domain.
  </Card>
  <Card title="Knowledge Base" icon="book-open" href="/agentic/knowledge-base">
    Render the published ontology as a portable, agent-readable wiki.
  </Card>
</Columns>