Autonomous agents is Reltio's conversational interface for working with your master data. Built on the Model Context Protocol (MCP) server, it allows you to explore, validate, and manage entity records through chat-based interactions with AI agents. These agents operate on live production data while honoring your organization role-based access control (RBAC), data masking, and audit policies.

Autonomous agents are designed for the following business and technical users who need to manage and govern master data in real time:

Data Steward Solution ArchitectSystem Administrator Data Product Owner

For more information about each of these user roles, see About roles.

How it works

You launch a conversation with a selected agent in the autonomous agents workspace. Agents use governed APIs (called tools) to read and act on entity data. Each interaction — whether it's a lookup, enrichment request, or merge action is scoped to your access level and fully auditable.

Discover agents

If you're logging in to autonomous agents for the first time, the Data explorer agent appears by default in the left panel under RELTIO AGENTS. To explore and launch additional agents, go to the Discover agents tab.

Agents are organized into two groups:

• Reltio autonomous agents — Prebuilt agents provided by Reltio.
• Custom agents — Agents built by or for your organization.

After you launch an agent, it appears in the left panel under RELTIO AGENTS and stays visible across sessions unless you remove it. The left panel shows the first five agents you add in the order you've launched them. Additional active agents are accessible by scrolling.

Agent types

Reltio supports two categories of agents:

• Included agents: Data explorer and Profiler agents do not consume credits, and are available to all autonomous agents users.
• Licensed agents: Such as the Resolver agent, operate on a credits-per-call basis.

For more information, see Autonomous agents catalog and Autonomous agents usage through Reltio.

Core concepts

Autonomous agents rely on a few key concepts that shape how you interact with your data:

• Conversation: A chat session between you and one agent, scoped to a specific task. The conversation retains context as you continue interacting.
• Agent: A software entity with agency: it can perceive context, reason about goals, and take actions on behalf of a user or system. Each agent uses approved tools to read, compare, or update data — depending on your permissions.
• Tool: A secure, governed capability the agent uses behind the scenes to complete an operation (for example: search, match, merge). Every call is logged and access-controlled.

Built-in safety and compliance

Every action an agent performs is routed through the MCP server. This ensures:

• All actions respect your RBAC policies and attribute-level masking
• Write operations (e.g., merges) are logged with timestamps and user attribution
• Agents can only use allowlisted tools and cannot access raw databases
• Agent behavior is constrained to your tenant's policies and data residency zones

When to use it

To begin using the interface, see Use the workspace in autonomous agents .

To navigate between autonomous agents and other Reltio applications, see Navigate between autonomous agents and other Reltio applications.