The admin agent
Administer ContextWorks by conversation: draft briefs from a document, check health, compare two entities, publish a draft after approving its exact content. It runs as its own Agentforce agent or MCP server, separate from the runtime tools — set it up on Deploy → Agentforce, step 3a or Deploy → MCP, steps 2a–6a. It requires the ContextWorks Admin or ContextWorks Domain Manager permission set, and every call runs as you — domain managers get their domains, not the org.
How it works
Three rules govern what the agent may do:
- Reads are unrestricted. Health, the change log, the catalog, the configuration graph — aggregates and configuration, never record data.
- Drafts reach no one. The agent composes briefs, skills, and entity text freely, because a draft serves no agent until it’s activated.
- Publishing needs your approval on exact content. Activating, binding to a domain, and deactivating each preview first: the response shows exactly what will serve (or how routing changes) plus a digest. The agent shows you the preview, and commits only with your yes and that digest. If the draft changed since the preview, the commit is refused — content you never saw can’t be published on an old approval.
What you can do
| You want to… | The agent uses |
|---|---|
| See what agents receive, per domain | Get Catalog |
| Check usage, quality, issues, trends, or writes | Get Health |
| See who changed what, and why | Get Change Log |
| Audit the configuration | Get Full Config |
| Draft a brief, a skill, or entity text | Save Draft |
| Publish a draft | Activate Draft |
| Change what a domain carries | Update Domain Contents |
| Pull something from service now | Deactivate |
| Run a packaged procedure | Get Skill · the skills |
Limitations
The agent cannot delete artifacts, change settings, grant access, or touch the write-access switches — those stay in the Studio and Admin tabs. Entity structure (fields, related lists, levels) is also Studio-only; the agent drafts entity text.