The product

Don't Build AI. Ship It.

Sidenet gives vertical SaaS companies the full stack — build, deploy, observe, and monetise AI assistants without building the plumbing.

Your SaaS app

Chat Copilot
How can I help you today?
Check guest in room 412
Guest Sarah Chen, checked in 2 days ago. Room 412, 4th floor.
initSidenet()

Embedded with 1 line of code

SideNet AI
⇅

SideNet Studio

Configurable with code or no code

  • 🎨Customise chat UX/UI
  • 🛠Build Agents & Workflows
  • 🔗Connect internal & external tools
  • 🧠Configure ST & LT memory
  • ⚙️Tune, version & evaluate assistants
  • 📊Monitor cost & performance
  • 💰Monetise your assistants

Build

Build agents, workflows, and networks.

Everything you need to go from zero to a working multi-agent system — models, memory, tools, and orchestration — configured visually in Studio.

One orchestrator. A team of specialists.

The orchestrator runs the room.

Build agent networks visually in Studio. One orchestrator reads every request and routes to the right specialist — or chains several together. Each agent gets its own prompt, tools, guardrails, and model.

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

Agents that delegate to other agents.

Guest ops invokes scheduling. Scheduling calls the calendar API. The calendar checks availability and books a slot. Your users see one clean answer — the orchestrator manages the chain behind it.

User Request0ms

"Book a spa appointment for the guest in 412"

Orchestrator45ms

Routing to Guest Ops Agent

Guest Ops Agent120ms

Delegating to Scheduling Sub-Agent

Scheduling Agent280ms

Calling Calendar API tool

Calendar API410ms

Available: 2:00 PM, 3:30 PM, 5:00 PM

Response520ms

"Booked: Spa at 2:00 PM for Sarah Chen, Room 412"

Add a new agent. Instantly routable.

The orchestrator routes dynamically based on intent, context, and the agents available — not hardcoded rules. No YAML, no decision trees, no rewiring.

Before
Pricing
Guest Ops
Analyst
+
Add F&B Agent
After
Pricing
Guest Ops
Analyst
F&B AgentRoutable

Assistants that remember.

Four memory modes — all configured in Studio, no code after setup.

ACTIVE NOTES

Picks up the essentials

Builds a working picture of each user — preferences, projects, context — and carries it forward between sessions.

CONVERSATION SUMMARY

Keeps notes as it goes

Tracks what's been said and decided as conversations grow. Never loses the thread.

LONG-TERM KNOWLEDGE

Re-reads the file

Retrieves actual excerpts from past conversations when something relevant comes up.

RECENT MESSAGES

Short-term awareness

Control how many recent messages stay in view. Dial up for complexity, keep lean for simple Q&A.

300+ models. Zero lock-in.

OpenAI, Anthropic, Google, Mistral, Meta, Cohere — 60+ providers. Best model for each agent. Swap in two clicks. New models within 24 hours of release.

OpenAI
Anthropic
Google
Mistral
Meta
Cohere
AWS Bedrock
Azure OpenAI
Together AI
Fireworks
Groq
Perplexity
DeepSeek
Replicate
Anyscale

60+ providers supported

Agents that take action, not just talk.

Platform keys or user tokens. Your call.

Connect 1,000+ external apps, your own internal APIs, or both. Platform credentials for internal services, per-user OAuth for their calendar or CRM — mix both in the same network.

🔑
Global Auth

One API key for all users

Analytics API
Internal Services
Reporting Engine
👤
User Auth

Per-user OAuth tokens

Google Calendar
Slack
Email

Paste your spec. Get agent-ready tools.

Paste an OpenAPI spec and every endpoint becomes an agent tool in seconds. No manual mapping, no SDK wrapping. Internal services become callable instantly.

https://api.hotel.com/openapi.json
Import
Extracted Tools✓ 5 tools found
GET/reservationsList all reservations
POST/bookingsCreate a new booking
PUT/guest-preferencesUpdate guest preferences
GET/availabilityCheck room availability
DELETE/bookings/:idCancel a booking

Deploy & Embed

From Studio to your product in minutes.

Two ways to access your agents — embed the Chat SDK directly in your product, or call them via API. Three isolated environments and instant rollback keep your customers safe.

Embed a copilot your users will think you built.

One function call. Done.

A branded, context-aware chat appears inside your product. It sees the page, the data, and the user's role — no extra context needed. Customise colours, fonts, icons, and welcome messages from Studio. Light and dark mode built in. Responsive, keyboard-navigable, feels native.

// Install and initialise
import { initSidenet } from '@sidenet/sdk'
initSidenet({
theme: 'dark',
position: 'right',
networkId: 'your-network-id'
})

Aware of what's on screen.

This isn't a generic chat window. The copilot sees the page, the data, and the user's role. A front desk agent asking about a guest doesn't need to specify which reservation — the copilot already knows.

Reservations > #4812
Guest: Sarah ChenChecked In
Room
412
Nights
3
Rate
$289
Type
Suite
Copilot

What's the guest's room preference?

Sarah Chen (Room 412) prefers king bed, extra pillows, and late checkout.

Context: Reservation #4812

Or skip the UI entirely.

Hit your agents directly.

Hit your agents and agent networks directly through the Sidenet API. Same orchestration, same tools, same memory — no frontend. Build custom interfaces, trigger agents from backends, or wire into existing workflows.

POST/v1/networks/{network_id}/chat
{
"message": "What's the occupancy forecast for next week?",
"user_id": "front-desk-sarah",
"context": {
"property_id": "hotel-412"
}
}

Three environments. Instant rollback.

Development, staging, production — fully isolated. Test in Studio, preview through the SDK in staging, promote when ready. Something break? Roll back in seconds, not sprints.

Studio

Build & test

Build and test agents in Studio. Full traces, logs, and debugging. Break things, tune prompts, and experiment safely.

Staging

Preview internally

Preview your network through the SDK in your staging environment — exactly what customers will see, before they see it.

Production

Ship with confidence

Promote to production when you're ready. Roll back to the previous version in seconds if anything unexpected happens.

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

Observe & Iterate

See everything. Improve constantly.

Full observability across every trace, thread, and tool call. Scoring catches regressions. User feedback closes the loop. Your assistants get measurably better every week.

Every decision, traced.

Drill into any span.

Each interaction generates a complete trace — orchestrator routing, agent execution, tool calls, response. Drill into any span for timing, tokens, cost, and exact I/O. When something breaks, you know exactly where and why.

Trace #a8f3k2Total: 520ms | $0.011
User Request
Orchestrator
45ms820$0.002
Pricing Agent
340ms2,140$0.008
Rate Tool Call
120ms
Response
15ms380$0.001

Conversations in full. Feedback built in.

Your users tell you what to fix.

See every conversation for any user, across sessions. Spot patterns, track resolution rates, review how context builds over time. Thumbs up/down and written feedback are collected directly in the copilot — filter by agent, time, or sentiment in Studio.

87%positive this week
↑ 3%vs last week
👍Pricing AgentGot the right rate instantly
👍Guest OpsBooked the spa perfectly
👎AnalystReport was missing weekend data
👍Pricing AgentAccurate comp set comparison

Catch regressions. A/B test everything.

Continuous scoring.

Code-based scorers for hard rules — valid JSON? Right tool called? LLM-based scorers for subjective quality — helpful? Accurate? On-brand? Runs continuously on a sample. Scores drop, you get flagged.

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

Test prompts with data, not opinions.

Compare prompt versions and model swaps side by side — v1 scored 4.1, v2 scored 4.5. Ship v2. Done.

Prompt v1Current
Helpfulness4.1/5
Accuracy4.3/5
Tone3.8/5
Avg: 4.07
Prompt v2Winner
Helpfulness4.5/5
Accuracy4.4/5
Tone4.2/5
Avg: 4.37

Track & Monetise

Is your AI making money?

Full cost ledger per customer, per assistant, per model. Simulate pricing before you ship. Monitor margins in real time.

Every cent, attributed.

No guessing. No surprises.

Cost per customer, per assistant, per model, per tool call. No guessing whether AI features are profitable. No month-end surprises.

Total Revenue
$44.00
Total Cost
$14.30
Avg Margin
69%
CustomerAssistantModelTokensCostRevenueMargin
Cascade SelectPricing AgentClaude Sonnet 4142k$4.12$12.0066%
Garden Hotels GroupGuest OpsGPT-4o98k$3.14$12.0074%
Express HospitalityAnalystGemini Pro67k$1.21$8.0085%
Metro Place HotelsPricing AgentClaude Sonnet 4201k$5.83$12.0051%

Simulate before you ship.

Commit with data, not assumptions.

Model usage-based, tiered, per-seat, or hybrid pricing. See how each strategy affects margins at different usage levels. Commit with data, not assumptions.

Monetisation Simulator
Pricing Model
Usage-based
Tiered
Per-seat
Price per 1K tokens
$0.08
Avg usage / customer
150K tokens/mo
Projected (100 customers)
Revenue
$1,200/mo
Cost
$420/mo
Margin
65%

Margins, in real time.

Revenue vs. cost, tracked live.

Revenue vs. cost, tracked live. Alerts when a customer's usage erodes your margin. Know which assistants drive profit and which drag it down.

Revenue vs Cost
Revenue
Cost
Jan
Feb
Mar
Apr
May
Jun
Alert: "Hyatt Place" margin dropped below 55% threshold

Get started

Live in days, not months.

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.