The launch and day-one guide set
Step-by-step guidance for workspace admins bringing the first agent, channel, and knowledge sources into production.

Onboarding · 9 min read
Launch your workspace
The operator path from a brand-new workspace to the first healthy live conversations, working through Agent Builder in order without skipping the validation that protects answer quality.
Agents · 6 min read
Create your first agent
Define a support agent in Agent Builder that is narrow enough to stay safe and useful enough to carry the first wave of live traffic.
Channels · 6 min read
Connect your first channel
Use the Connections section to bring in one live support channel, verify health, and confirm the route lands on the intended workspace without hidden gaps.
Knowledge · 7 min read
Add website and FAQ knowledge
Use the Knowledge section to ground the agent in one reliable help source so answers stay specific instead of slipping into generic support language.
Builder & Playground · 6 min read
Validate and refine before launch
Pressure-test the agent in the Launch section and tune behavior in Train, so the first live week teaches you about edge cases, not avoidable setup mistakes.
Inbox · 5 min read
Review your first conversations in Inbox
Use the first live transcripts in Inbox to confirm routing, answer quality, and the places where the rollout still needs guardrails.
Analytics · 5 min read
Read your first analytics baseline
Use the first Analytics pass to understand demand, activity, and where the workspace is healthy versus merely configured.
Settings · 4 min read
Manage workspace settings and access
Keep the workspace operable by confirming who owns rollout decisions, who can change configuration, and where tenant settings affect the live experience.
Billing · 4 min read
Understand billing and usage basics
Read plan posture, capacity, and early usage signals in Billing without turning the first pass into a finance project.
Troubleshooting · 7 min read
Common launch blockers
Diagnose the first rollout failures quickly: connection not live, knowledge not indexed, no responses, no conversations, or access confusion across the team.