Agent Configuration

The AI agent is configured per project. It uses project knowledge, conversation context, customer memory, guardrails, and model settings to suggest, draft, or send replies.

Modes

ModeBest for
AssistTeams that want suggestions but no automatic drafts.
CopilotTeams that want AI drafts reviewed by humans.
AutopilotTeams with strong knowledge coverage and clear escalation rules.

Configuration Areas

TabPurpose
ConfigurationMode, model, tone, prompt, temperature, and response settings.
TestRun controlled questions against the current agent configuration.
KnowledgeInspect the articles, crawls, docs sites, and vector sources available to the agent.
GuardrailsRequire citations, redact PII, limit answer length, and define escalation topics.
ImprovementsTrack missing knowledge and suggested changes.
MemoryProject-level memory, history, pending changes, and rollback.

Guardrails

Guardrails are evaluated before an answer becomes customer-facing. Common guardrails include:

  • require citations
  • redact PII
  • disallow unsafe or unsupported topics
  • escalate certain topics
  • cap answer length
  • require human approval for actions

BYOM

RogerIQ supports bring-your-own-model flows through model provider configuration. Store model credentials only in server-side settings, never in browser code.

Testing

Run test questions before switching to Autopilot. Use examples from real tickets and include edge cases:

  • missing docs
  • angry customers
  • refund requests
  • ambiguous account identity
  • policy exceptions
  • security-sensitive questions

Autopilot should be earned by test results, not enabled because the demo looked good once.

Ask a question... ⌘I