# Exmergo Ace: The Agent Context Engine | Exmergo

> Exmergo Ace is the Agent Context Engine. It turns your governed semantic layer into agent-ready context, so every agent (Exmergo Viz, your own custom agents, and the coding agents your team uses) grounds on one audited source, under the same RBAC, PII policy, and audit.

Agents are only as good as the context they stand on. Point them at raw SQL and they invent joins, miss metric definitions, and surface data they were never meant to see. Ace sits between your governed semantic layer and every agent that consumes it, serving grounded, permission-aware context so answers stay correct, consistent, and auditable, no matter which agent asks. Many agents, one governed context.

## The Agent Context Engine

Ace is the single context interface every agent connects to. It turns the dbt models, metrics, and join paths that Dex maintains into structured, agent-ready context, so agents reason over real definitions instead of guessing at schemas. The same governed layer is open to Exmergo Viz, any custom agent your team builds, and the coding agents you already use.

## Capabilities

### One interface, every agent

Ace is the single context interface every agent connects to. Exmergo Viz, your own custom agents, and the coding agents your team already uses all read from the same place.

- One connection point for Viz, custom agents, and coding agents
- No bespoke integration per agent: connect once, ground everywhere
- Add a new agent without re-plumbing your data access

### Grounded context, not raw SQL

Ace serves your dbt models, metrics, and join paths as structured, agent-ready context. Agents reason over definitions instead of guessing at schemas.

- Metrics and dimensions served with their real definitions
- Verified join paths, so agents never invent relationships
- Answers that match the numbers your team already trusts

### Governed by default

Opening your data to agents should not mean opening it up. Ace enforces your access model on every request, so each agent sees only what it is allowed to.

- Role-based access control and workspace-level permissions
- PII policy enforcement on every agent query
- Full access audit trails, from prompt to answer

### Always in sync

Ace grounds on the same governed layer Dex maintains, so agents never work from a stale copy. When the semantic layer changes, every agent sees it.

- One source of truth shared by every consumer
- Definitions stay current as Dex authors and maintains them
- No drifting exports or duplicated modeling per agent

## How Ace Works

1. **Point Ace at your governed layer.** Ace connects to the dbt models and semantic layer Dex maintains as your single source of truth.
2. **Ace serves agent-ready context.** Definitions, metrics, and join paths become grounded, permission-aware context, never raw SQL.
3. **Every agent queries one source.** Viz, your custom agents, and coding agents all ground on the same audited layer, under the same RBAC, PII policy, and audit.

## Governed From the First Query

Ace applies your access model to every agent request, so grounding more agents never widens your exposure.

- Role-based access control (RBAC) and workspace-level permissions
- PII policy enforcement on every agent request
- Full access audit trails for every agent and query
- Clear lineage, from governed model to agent answer

## Frequently Asked Questions

**What is Exmergo Ace?**
Ace is Exmergo's Agent Context Engine. It sits between your governed semantic layer and the agents that consume it, turning dbt models, metrics, and join paths into agent-ready context. Every agent, Exmergo Viz and any custom agent you build, grounds on the same audited layer through Ace, under the same RBAC, PII policy, and access audit.

**How is Ace different from connecting an agent straight to my warehouse?**
A raw warehouse connection gives an agent tables and SQL, so it has to guess at joins, metric definitions, and which columns it may read. Ace serves the governed semantic layer instead: verified join paths, real metric definitions, and permission-aware context. Agents reason over meaning rather than schema, and every request is bound by RBAC and PII policy.

**Which agents can use Ace?**
Ace is one context interface every agent connects to: Exmergo Viz for self-serve dashboards, any custom agent your team builds, and coding agents such as Claude and Cursor. Connect once and every agent grounds on the same source, with no bespoke integration per agent.

**How does Ace keep agents from drifting out of sync?**
Ace grounds on the same governed dbt models and semantic layer that Dex authors and maintains, so there is one source of truth rather than a copy per agent. When a definition changes, every agent sees the change, so answers stay consistent across Viz and your own agents.

**Is Exmergo Ace available today?**
Not yet. Ace is in private preview and is not generally available. It will be part of the Exmergo Enterprise platform, which today includes Exmergo Viz and Exmergo Dex. We are working with a small group of design partners while we build it, and you can apply to join them: https://www.exmergo.com/contact-sales

## Become an Ace design partner

Ace is in private preview. We are working with a small group of design partners to ground their agents on one governed context layer, and shaping Ace around what they need. Apply here: https://www.exmergo.com/contact-sales