How it works

Live in days, not months.

Four steps from zero to a production AI assistant your customers actually use.

Step 1

Embed the chat

One SDK call. A branded, context-aware copilot appears inside your app. Production-ready from the first line.

// Install and initialise
import { initSidenet } from '@sidenet/sdk'
initSidenet({
theme: 'dark',
position: 'right',
networkId: 'hotel-ops'
})
Hotel PMS · Reservations
GuestRoomStatus
Sarah Chen412 SuiteChecked in
M. Johnson308 DeluxeArriving
R. Patel201 StandardCheckout
🤖
Hotel Copilot
Draft a pre-arrival note for Sarah Chen
Hi Sarah! Your Suite 412 is ready — we've noted your king bed preference...
Ask anything…
Step 2

Build your agent network

Create an orchestrator and specialist agents in Studio. Assign tools, prompts, memory, and sub-agents — visually.

OrchestratorRoutes requests dynamically
Pricing
Rate APIComp Set
Guest Ops
PMSCalendar
Analyst
BI DataReports
Compliance
Policy DB
Scheduling
CalendarStaff
Step 3

Test, preview, ship

Three environments. Test internally, preview in staging, promote to production. Roll back in seconds.

StudioTesting
Pricing v3
Guest Ops v2
New: F&B Agent
StagingReview
Pricing v2
Guest Ops v2
ProductionLive
Pricing v2
Guest Ops v1

Each environment is fully isolated — no shared state or config

Step 4

Monitor and improve

Traces, feedback, scoring, usage analytics. Your assistants get measurably better every week.

Helpfulness Score — Pricing AgentLast 7 days
4.2Mon
4.3Tue
4.1Wed
4.2Thu
!
3.1Fri
3.8Sat
4.1Sun
Regression detected: Pricing Agent dropped to 3.1 on Friday

Stop building AI infrastructure. Start shipping AI products.

Embed the copilot. Build your agents. Iterate in Studio.