Skip to main content
Deployments connect your agents to real customer channels, defining when and how agents respond to incoming messages.

​
What is a Deployment?

A deployment is the connection between:
  • An agent — What responds
  • A trigger — When to respond
  • A mode — How to respond

​
Deployment Components

​
Agent

The configured AI that handles conversations. Includes:
  • Runbook or workflow
  • Knowledge access
  • Guidelines and guardrails
  • Classification settings

​
Trigger

What causes the agent to activate:
ComponentExamples
ChannelZendesk, Slack, Intercom, Discord
EventNew ticket, message received, comment added
FiltersSpecific channels, groups, tags

​
Mode

How the agent interacts with customers:
ModeBehavior
LiveResponds directly to customers
ShadowDrafts responses for human review
TestingRuns in isolation for validation

​
Status

  • Active — Deployment is running
  • Paused — Temporarily disabled

​
Deployment Lifecycle

Create → Configure → Test → Activate → Monitor → Iterate
1

Create

Define the agent and trigger
2

Configure

Set mode, filters, and options
3

Test

Validate in playground or shadow mode
4

Activate

Enable for real traffic
5

Monitor

Watch performance metrics
6

Iterate

Adjust based on results

​
Multiple Deployments

You can create multiple deployments for flexibility:

​
Same Agent, Different Channels

Support Agent → Zendesk tickets
Support Agent → Slack messages
Support Agent → Intercom conversations

​
Different Agents, Same Channel

Billing Agent → Zendesk (billing group)
Technical Agent → Zendesk (technical group)

​
Different Events

Support Agent → New tickets only
Triage Agent → All ticket updates

​
Deployment Cards

Each deployment card shows:
  • Agent name — Which agent is deployed
  • Trigger — Channel and events
  • Mode — Live, Shadow, or Testing
  • Status — Active or Paused
  • Metrics — Recent activity

​
Best Practices

​
Start in Shadow Mode

New deployments should start in shadow mode:
  1. Agent processes real messages
  2. Responses saved as drafts/internal notes
  3. You review before going live
  4. Build confidence, then switch to live

​
Monitor Closely Initially

After going live:
  • Check run history frequently
  • Watch for unexpected behavior
  • Review escalation rates
  • Gather customer feedback

​
Use Filters Strategically

Start narrow and expand:
  1. Deploy to one channel first
  2. Expand to more channels when confident
  3. Use tag filters to control scope

​
Next Steps

Create Deployment

Deploy your first agent

Deployment Modes

Understand live vs shadow

Triggers & Events

Configure when agents respond