AI IN
Agent Consumer
The business uses agents across desktops, SaaS, and owned systems. Govern a broad and fragmenting array of sources.
Explore the platform ↗Govern the agents you use, and the agents you ship.
Every enterprise now consumes agents and increasingly ships them. Dome is the operations layer underneath both: one authentication model, one policy engine, one audit trail.
Patterns of enterprise agents
Two directions.
One control plane.
AI OUT
Agent Provider
The product ships agents to customers, or exposes an MCP surface they can drive. Operate the API and tool layer together.
Explore the platform ↗CONTROL
Connect / Govern / Operate
The same three phases apply to every agent, regardless of framework or cloud.
Use cases
Pick the operational pain to solve first.
Most engagements start with one concrete job. Each maps to a control point and composes with the others as the estate grows.
01 / REGISTRY
Onboard agents
Register every agent against a single tenant. Bring them under authentication, authorization, and audit from day one.
Read more ↗02 / GATEWAY
Consolidate tool access
Put every MCP and tool call behind one gateway. Limit access, enforce policy, audit every action.
Read more ↗03 / BROKER
Broker model access
Route model traffic on policy, cost, and availability without rewriting agent code.
Read more ↗By role
Built for platform, security,
and finance teams.
01
Platform teams
Run one operations layer across the agentic estate. Unblock the org without absorbing every team's tooling debt.
02
Security
Authentication for every agent, policy as code, attribution end-to-end. Audit what was decided, not just what was logged.
03
Finance
When code is cheap, governance is scarce. Consolidate model and tool spend before it fragments.