What are Agent Stacks?

An Agent Stack is Atender’s AI customer service team — a virtual agent that handles inbound conversations from end to end. To customers it looks like a single helpful person with a name and an avatar. Under the hood it’s a layered system: a router that picks who handles the message, an orchestrator that watches the conversation and intervenes when things go off the rails, and a set of specialist agents that each have deep knowledge of one area.

A stack can run on whichever channels you enable — email, web chat, SMS, voice, WhatsApp, Messenger, the API channel — and conversations it’s working on appear in the Alia tab of Conversations so your team always has visibility into what the AI is doing.

Name it whatever you want

You’re not stuck calling it “the AI.” Each stack has its own name, description, icon, color, and avatar. Customers see whatever you call it — Sophie, James, Alia, Atender Bot — and the only place the word “Alia” appears in the product itself is on the inbox tab that lists AI-handled conversations.

What’s inside a stack

The stack isn’t one prompt. It’s three layers working together:

• Router — Reads the customer message, picks which specialist should handle the topic
• Orchestrator — Watches the whole conversation, detects stalls, re-routes when needed, escalates risky situations to humans
• Specialist agents — The experts. Each one has its own scope, instructions, knowledge access, and capabilities

The more specialists you add, the more capable the stack becomes. A stack with one generalist will never match a stack with five focused experts — each can have its own scope, its own instructions, and only the knowledge and capabilities relevant to its area. See Anatomy of an Agent Stack for the full architecture, and What is a specialist agent? for what makes a good specialist.

Knowledge sources

Agent Stacks pull from four kinds of knowledge:

• Knowledge Base — your customer-facing help articles. The AI can quote and link to these.
• Handbook — your internal procedures and policies. The AI uses these to guide its behavior but never quotes them directly to customers.
• Incidents — active service disruptions. The stack is automatically aware of ongoing issues so it doesn’t tell a customer “everything’s fine” while a known outage is in progress.
• Internet search — optional per specialist, with a configurable URL allow-list so the AI only searches sources you trust.

Capabilities — agents that can act

Without capabilities, an Agent Stack can only talk. With capabilities, it can act — look up an order, process a cancellation, check delivery status, verify account ownership, or call any external API you connect. Each specialist gets only the capabilities it needs, so a billing agent can issue refunds while the product agent can only look things up.

Handing off to humans

The orchestrator runs a state machine over every conversation. When it detects a stall, a frustrated customer, an escalation request, or a topic the stack can’t handle, it triggers handover. You control how this happens via the Handover tab — required information the AI must collect before handing off, the team that picks up, and what happens outside opening hours. See Handover to humans.

Testing and tuning

Every stack has a built-in test sandbox. You can chat as a customer, see how the router routes, watch which specialist responds, and flag any reply that missed the mark. Flagged responses feed the Tuning flow — Atender analyzes what went wrong, proposes concrete changes (system prompt edits, routing rule tweaks), and you apply or revert them with a click. The same flagging signal also drives Self-Learning, which proposes improvements based on patterns across many real conversations.

Where to start

• Build your first stack: Create an Agent Stack
• Understand the architecture: Anatomy of an Agent Stack
• Add expertise: Add a specialist agent
• Tune the personality: Set the stack personality
• Hand off correctly: Configure handover