Ontology Reasoner

How to Use the Ontology Reasoner

The Ontology Reasoner is one of the tools available from My Tools on the ARPIA Home screen. It lets you explore your organization's knowledge nodes with Oria, an agentic assistant that can answer questions, run semantic and ontology queries, and build visualizations directly from your data.

Overview

Tool nameOntology Reasoner
AssistantOria (agentic assistant)
Access fromARPIA Home → My Tools → Ontology Reasoner, or ARPIA Home → Side Menu (left) → Ontology Reasoner
Core capabilityAsk questions, run semantic/ontology queries, and build visualizations over your knowledge nodes
Screenshot: Ontology Reasoner tool card on ARPIA Home

Use Cases

Ontology Reasoner is built for exploring relationships in your data, not just retrieving records — so it's most valuable in situations where the connections between things matter as much as the things themselves.

  • Knowledge discovery for new team members. Instead of asking a colleague "how does X relate to Y" or hunting through scattered docs, a new hire can ask Oria directly (e.g., "what data nodes feed into the Security Committee dashboard?") and get an answer grounded in the actual ontology.
  • Governance and compliance mapping. Before changing an access policy or data flow, ask Oria to trace dependencies (e.g., "what systems or reports depend on this node?") to understand blast radius before making the change — useful in security/governance reviews like Comité de Seguridad prep.
  • Cross-domain analysis. When a question spans multiple areas (CX, security, ops, finance), Oria can query across ontology nodes you have access to and surface connections a single-domain search wouldn't reveal.
  • Pre-change impact checks. Before deprecating a doc, table, or workflow, ask what's connected to it — this surfaces hidden dependents before you break something downstream (same principle as checking dependencies before archiving a doc).
  • Building visual artifacts for stakeholders. Use a session to generate a relationship diagram or summary you can pin as an Artifact and share in a meeting or report, rather than manually re-explaining the structure each time.
  • Ad-hoc investigation. During an incident or audit, spin up a session scoped to just the relevant nodes and ask targeted questions instead of manually piecing together context from multiple tools.

How you'd typically use it: open a session scoped to the specific nodes relevant to your question (not the whole ontology), ask a direct question, and pin anything reusable to Artifacts before closing the session — session names should reflect the question, not just the date, so they're findable later.

Prerequisites — Admin Configuration Required

Ontology Reasoner does not work out of the box. Before any user can run a session, an ARPIA admin must configure a Model Group for it. If this is left unset, Ontology Reasoner (and the model picker inside a session) is disabled.

Screenshot: "Configure Model Group" prompt shown inside a session

Admin steps

  1. Go to ARPIA / AI Governance / Configuration.
  2. Under Global AI Configuration, confirm AI is enabled for the work-area (Enable AI in this work-area = Yes).
  3. Under Manage Model Groups, create the group of LLMs you want available (e.g., openai/gpt-5.5).
  4. Back in Global AI Configuration, under Assistant Model Groups, set:
    • Arpia Ontology Reasoner — Model Group (required) — restricts Ontology Reasoner to this group's models, in order. If left unset, Ontology Reasoner is disabled.
    • Arpia Ontology Reasoner — file object store (required for uploads) — the object-store bucket where files uploaded during an exploration are saved, so the file-reader can fetch them. Leaving this as "None" disables document uploads in Ontology Reasoner.
  5. Click Save Configuration.

Screenshot: Global AI Configuration page with Assistant Model Groups section

Note: This same configuration screen also sets the Oria (Workshop & SPA) — Model Group, which is a separate, equally required setting for Oria inside Workshop objects and the SPA builder. Both are independent and must each be configured — setting one does not configure the other.

Getting Started

  1. From ARPIA Home, select Ontology Reasoner — either under My Tools, or from the Side Menu on the left.
  2. You'll land on the Oria workspace. If you have no sessions yet, you'll see:

    Explore your Ontology with Oria — Create a session, add the nodes you have access to, and ask questions.

  3. Click the + next to Sessions (top-left panel) to start.

Screenshot: Empty Oria workspace with "Explore your Ontology with Oria" state

Creating a New Session

  1. Click + in the Sessions panel.
  2. In the New session dialog, enter a descriptive Name (e.g., Q3 margin analysis).
  3. Click Create to open the session, or Close to cancel.

GIF: Creating a new session via the New Session dialog

Tip: Use a name that reflects the question or analysis you're running — sessions are listed for later reference, so a clear name saves time when you come back to it.

The Session Workspace

Screenshot: Full Ontology Reasoner session workspace (3-panel layout)

Once a session is open, the workspace is organized into three areas:

Left Panel — Sessions

  • Search sessions to find previous work.
  • Scheduled Tasks: you can save scheduled query definitions here. As of this writing, the scheduling engine is not yet enabled — definitions are saved and will run automatically once the engine is activated.

Center Panel — Oria Chat

  • This is where you interact with Oria directly: type your question in the "Ask about your data…" box.
  • You can attach files or switch the underlying Model used for the session from the controls at the bottom of the chat box.

Right Panel — Session Configuration

This panel controls what Oria has access to and produces within the session:

Screenshot: Right-hand configuration panel — Ontology Nodes, Tools, Artifacts, Files

SectionPurpose
Ontology NodesChoose which knowledge nodes you have access to and want included in this session. Empty by default — "Open a session to choose nodes."
Tools in this sessionAdd tools the agent may use (e.g., Search Engine, Image Search).
ArtifactsPinned results from the session appear here for quick reference.
FilesUpload files for Oria to read alongside your ontology data.

Typical Workflow

  1. Create a new session with a clear name.
  2. Add the relevant Ontology Nodes you want Oria to reason over.
  3. (Optional) Add any extra Tools the agent should have access to.
  4. (Optional) Upload supporting Files.
  5. Ask your question in the chat box.
  6. Pin useful results to Artifacts for later reuse.

Known Limitations

  • Requires admin setup: Ontology Reasoner is disabled until an admin configures a Model Group for it (see Prerequisites above). This isn't a per-user setting — it's set once at the work-area level.
  • Scheduled Tasks: the scheduling engine is not yet active. Scheduled definitions are saved but will only begin running once the engine is turned on — no notification is currently given for this state beyond the in-app note.

Did this page help you?