Tenant: primeassist-dev

P26 dashboard skeleton — module pages land in M2+.

Agents · Support Agent

Support Agent

Slug support. Confidence threshold 0.70. No policy pack attached.

Quality & regression

Wires the M6 B2 regression-on-save gate. When a non-off policy is paired with an active golden set, every save to this agent (and to its KB, tools, or policy pack) queues aconfig_save eval run. The save commits or reverts based on the run's result.

Require approval on save

Policy pack

Pick a pack to apply topic rules + refusal templates + optional confidence-threshold override on this agent's turns. Detach by selecting "(no policy pack)".

Persona

first-line policy support

Allowed risk classes

Sets which tool risk classes this agent is permitted to invoke. Tools whose risk class is not allowed are filtered out of the LLM-facing menu AND refused by the executor (belt and braces). Default is info-only — widen explicitly to grant change or sensitive access.

Attached tools

The LLM only sees tools attached to this agent. Save replaces the attachment set atomically. A risk class badge per tool flags when a sensitive tool is attached to an agent that is not permitted to call it — useful early-warning when provisioning.

No tools defined in this org yet. Create one under Tools.

Versions

Every save snapshots the agent. Restoring an older version appends a new entry — history is append-only.

#NoteWhen
v3currentrestored from v15/12/2026, 3:59:24 PM
v2tools attached5/12/2026, 3:59:21 PM
v1tools attached5/12/2026, 3:59:17 PM