Skip to content

Agent Configuration

Each AI agent can be independently configured to control which context items it receives. This goes beyond simple scope subscriptions -- you can override context selection at the per-agent level.

Accessing agent context settings

There are two ways to reach the agent context configuration:

  1. Go to /admin/ai/context/settings/agents and click Edit on an agent
  2. From the agent edit form at /admin/config/ai/agents, expand the Context Control Center section and follow the link

The per-agent edit form is at /admin/ai/context/settings/agents/{agent_id}/edit.

Configuration options

Scope subscriptions

Agents can subscribe to specific scope values to prioritize relevant context items. For example, an agent working in the Canvas editor might subscribe to the "Working in canvas" use case scope, while a content writing agent might subscribe to "Writing words".

Subscriptions are available for scopes that support them. Some scopes -- like Global and Target Entity -- do not use subscriptions because they apply automatically based on context.

See Scopes for details.

Always include

Specific context items that should always be included when this agent runs, regardless of scope matching or relevance ranking. Use this for critical context that an agent must always have access to (e.g., brand guidelines, compliance rules).

Never include (excluded items)

Specific context items that should never be included for this agent, even if they would otherwise match by scope or relevance. Use this to prevent irrelevant or conflicting context from reaching a particular agent.

Assigned items

Manually assign specific context items to an agent. Assigned items are considered during relevance matching and are prioritized over unassigned items that happen to match by scope.

How context selection works

When an agent runs, the context selection pipeline works as follows:

  1. All published context items are loaded
  2. Items are filtered by the agent's configuration (always include, never include, assigned items)
  3. Global items are automatically included
  4. Entity-targeted items are matched against the current entity context
  5. Remaining items are scored by scope matching against the agent's subscriptions
  6. The router ranks items by relevance (keyword or LLM strategy)
  7. Items are rendered within the configured token budget
  8. The final context text is appended to the agent's system prompt

Agents listing

The agents settings page at /admin/ai/context/settings/agents lists all configured agents and their current context settings. From here you can configure each agent's context independently.