What is a Specialist Agent?
A specialist is one focused AI agent inside an Agent Stack. It handles a specific kind of question — orders, cancellations, returns, billing, technical support, onboarding — and only that. The router picks which specialist takes each message; the specialist replies.
The single biggest lever you have over how well an Agent Stack performs is how you slice the work into specialists. A stack with one generalist will always be weaker than a stack with five focused specialists, because each specialist can have its own scope, its own instructions, and only the knowledge and capabilities it actually needs.
What a specialist is made of
When you open a specialist from the orchestrator canvas, the Setup tab shows three fields and a few derived counters at the top.
- Agent Name — Internal identifier (also shown to customers if router exposure is enabled) — “Billing Support”
- Responsibility (Scope) — What this specialist handles. Used by the router to pick who answers — “Billing, invoices, refunds, subscription changes”
- Instructions — Specialist-specific behavior — required steps, things to always do, things to never reveal, escalation triggers, reply format — “Confirm account email before issuing refunds. Hand off charges older than 90 days.”
That split — Scope vs. Instructions — is important. Scope is what topics come here. Instructions is how to behave once a topic is here. Don’t put tone in either; tone lives on the stack’s Personality tab.
Scope is what the router reads
The router uses LLM-based topic matching to decide which specialist takes a message. It looks at three signals:
- The Scope field on each specialist (the responsibility text).
- Any Routing topics explicitly attached to a specialist.
- Any Routing rules appended to the orchestrator’s prompt.
Most stacks only need a clear Scope per specialist. Routing topics are an explicit override when LLM matching is missing something obvious; the orchestrator-level routing rules are for global preferences (“prefer Billing over Tech for refund questions”). See Define routing topics.
A specialist with empty Scope and no routing topics shows a “No routing signals” warning on its canvas card — the orchestrator will struggle to route to it. Fill in the Scope at minimum.
Knowledge access — per specialist
Every specialist independently controls which knowledge it can read.
- Knowledge Base — pick “All” or select specific categories. Customer-facing articles. Quoted and linked in replies.
- Handbook — pick “All” or select specific categories. Internal procedures. Used to guide behavior, never quoted directly to customers.
A technical-support specialist might have access to the troubleshooting KB category and the technical-procedures Handbook category. A billing specialist might have a different scope — refund policies in the Handbook, billing FAQs in the KB. Tighter scope = faster, more accurate retrieval.
See Give a specialist knowledge access.
Capabilities — per specialist
Capabilities are the actions a specialist can take in external systems. Each specialist gets only the capabilities it needs:
- The order tracker gets the order-lookup capability.
- The billing agent gets the refund and invoice-lookup capabilities.
- The product expert gets nothing acting — just KB access.
Each capability assignment can override the default security level. L0 = always available, L1 = after the customer claims an identity, L2 = after OTP, L3 = after full authentication. So an order-status lookup might be L0 (anyone can ask “where’s my order”), but a refund action is L3.
Playbooks — multi-step procedures
A playbook is a deterministic procedure the specialist follows for a specific task — “process a return,” “verify identity,” “escalate a complaint.” Playbooks live under each specialist’s Playbooks tab and can be edited as a visual canvas.
Playbooks are useful when the LLM is reliable for one-off answers but inconsistent for multi-step flows where order matters. If your specialist sometimes skips the “did you turn it off and on again” step, a playbook makes sure it doesn’t.
The catch-all specialist
Every stack can designate one specialist as the catch-all. When the router can’t confidently match a message to any specialist, it routes to the catch-all instead of refusing. Useful as a friendly “I’ll find someone who can help” specialist that triggers handover or asks a clarifying question. Look for the star icon on the canvas.
Specialists are precise, not creative
Specialist temperature is forced to 0 at runtime. The temperature column exists in the schema because Self-Learning writes adjustment proposals there, but in practice every specialist replies deterministically. If you want personality, that’s the Personality tab — voice and tone are stack-wide.