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:- Start mode and instructions
- Knowledge access
- Guidelines and guardrails
- Tool access
- Classification settings
Trigger
What causes the agent to activate:Mode
How the agent interacts with customers:Status
- Active — Deployment is running
- Paused — Temporarily disabled
Deployment Lifecycle
1
Create
Define the agent and trigger
2
Configure
Set mode, filters, and options
3
Test
Validate in playground or testing 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
Different Agents, Same Channel
Different Events
Recurring Work
Deployment Cards
Each deployment card shows:- Agent name — Which agent is deployed
- Trigger — Channel and events
- Mode — Live or Testing
- Status — Active or Paused
- Metrics — Recent activity
Best Practices
Start in Testing Mode
New deployments should start in testing mode:- Agent processes real messages
- Responses can be saved as internal notes
- You review before going live
- 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:- Deploy to one channel first
- Expand to more channels when confident
- Use tag filters to control scope
Next Steps
Create Deployment
Deploy your first agent
Deployment Modes
Understand live vs testing
Custom Webhooks
Trigger agents from custom JSON events
Scheduled Deployments
Run agents on a recurring schedule
Triggers & Events
Configure when agents respond