Skip to content
DENDRITES AI

SERVICEORBIT

From a few words
to a routed ticket.

ServiceOrbit is a multi-tenant AI service desk. A requester chats, talks, or emails in plain language — the engine detects intent, grounds in policy, parses the evidence, checks eligibility, and drafts a complete, routed ticket. No forms.

It covers the whole lifecycle — intake, approval, fulfilment, archive — with an AI assessment for every approver and SLA clocks that keep their own time. And a Service Engine that authors new catalogue services from a department's real documents.

Interactive demo · five sample tenants · no sign-up to look around

serviceorbit.ai

ServiceOrbit · Shared Services Assistant

Live intake · builds the ticket as you talk

I need my research software licence renewed before Friday.
Got it — that's Software Licence Renewal. I've pulled the policy and your eligibility. Could you attach the grant approval PDF? Matched: Catalogue · IT Services › Licensing
TK

Ticket #SO-4821 · drafted

Eligible
Service · Licence Renewal
Priority · High · SLA 2d
Evidence · Grant PDF ✓
Route · IT Approver

AI recommendation: Approve — all 3 policy criteria met, evidence authentic.

No forms

The assistant builds the request itself — the requester just describes the need.

Every field traced

Each value on the ticket links back to the policy clause or document it came from.

AI + human

The engine knows when to decide and when to route to a person for judgement.

INTAKE, IN PLAIN LANGUAGE

Your team stops filling in forms.

A requester describes what they need — by chat, by voice, or by email — and the assistant does the rest: it finds the right service, asks for exactly what's missing, reads the attachments, and hands a clean, decided ticket to the approver. The work moves; nobody wrestles a portal.

A professional describing a request aloud while glancing at her laptop, mid-conversation, a colleague at work behind her.
ServiceOrbit · conversational intake

THREE WAYS IN

Chat. Voice. Email. One engine behind all three.

Whichever way a request arrives, the same intelligence runs underneath — intent detection, policy grounding, document parsing, and a drafted ticket at the end.

Chat

Requester

A proactive assistant identifies the right catalogue service by purpose and audience, asks one question at a time, and builds the request itself. The requester never fills in a form.

Voice

Requester

A live speech-to-speech agent (OpenAI Realtime over WebRTC) that builds the ticket as you talk — natural conversation, structured outcome, ephemeral keys minted server-side.

Email

Department inbox

Inbound department email is auto-triaged into a routed, AI-drafted reply — the same intent detection and policy grounding, applied to the channel your requesters already use.

ServiceOrbit Chat channel — the assistant grounds the request in policy, lists the matching clauses, and auto-assembles the requirements checklist while the live-request stages verify on the right.
Chat — a plain-language message becomes a policy-grounded ticket as you type. The stage tracker fills in live.
ServiceOrbit Voice channel — a live speech-to-speech assistant with an avatar, a running transcript, and a 'tap to start the call' control, building the request as the caller talks.
Voice — a live speech-to-speech agent that understands the request and builds the ticket as the caller talks.
ServiceOrbit Email channel — an inbound department email triaged into a routed, policy-aware AI-drafted reply; the agent can approve & send, edit, or escalate, and nothing sends without approval.
Email — an inbound department email is triaged and answered with a policy-aware drafted reply, flagged with exactly what's missing. The agent approves, edits, or escalates — nothing sends without a human.
ServiceOrbit Enquiry Matrix — the categorization framework the engine runs on: a library of request templates (registration, course withdrawal, scheduling, fees, appeals and more) with category tags and SLAs, plus an out-of-scope redirect path.
Enquiry Matrix — the categorization the engine runs on: a governed template library of request types, each with category tags and SLAs, so every inbound message is classified before it's answered. Anything off-scope is recognised and redirected.

THE FULL LIFECYCLE

Eight stages, intake to archive.

The engine injects an LLM at every point where it adds value — and stops where human judgement belongs. This is the orchestration map the platform actually runs.

01

Converse & detect intent

Plain-language chat, voice, or email. The assistant identifies the right service by purpose and audience.

02

Ground in policy

Pulls the service’s policy clauses, rules, exclusions, and the requirements checklist.

03

Parse documents

Extracts structured fields from PDF/image uploads via vision — in-memory; only extracted fields persist.

04

Evaluate eligibility

Checks each criterion against the requester profile and the submitted evidence.

05

Decide

Proceeds, routes to a human approver, holds for a fix, or declines — and knows when not to auto-decide.

06

Draft the ticket

A legible, structured ticket where every field traces back to its source.

07

Route the workflow

A persisted AI assessment per approver — recommendation plus per-criterion verdicts judged against the actual policy.

08

Track SLA & status

Business-hours SLA clocks that pause on “waiting for requester,” proactive updates, and outbound Slack notifications.

SEE IT RUNNING

The actual product, up close.

Screenshots from the live ServiceOrbit demo — the orchestration map, the approver console and its queue, and the requester's status page. The demo runs the Knowledge Unit tenant; the engine is the same for every desk.

ServiceOrbit Lifecycle — the orchestration map showing all eight stages of the ticket life cycle, with which steps the AI runs and which keep human judgement.
Lifecycle — one engine across the whole life cycle. Eight stages, six AI-run, two human decisions; every hand-off carries context forward so nothing is re-asked or re-typed.
ServiceOrbit Console — an AI-drafted ticket for a staff approver: structured request, an engine recommendation with one-click decisions, and an evidence panel where every field is traced to its source document.
Console — the same request as a clean ticket: structured fields, a recommendation judged against the policy, and evidence traced to the document it came from. Approve, request more info, or decline in one click.
ServiceOrbit Console queue — the approver's inbox: every AI-drafted ticket with its status and SLA countdown, filterable by Pending, Awaiting info, Approved, Declined and Closed.
Console queue — every AI-drafted ticket in one inbox, each with its status and SLA countdown. Filter by Pending, Awaiting info, Approved, Declined, or Closed; open any one to decide.
ServiceOrbit Track — the requester's live status page: an SLA ring, stage-by-stage progress, and a proactive chat thread of status updates from the assistant.
Track — the requester's side: an SLA ring, stage progress, and a proactive thread that keeps them posted. "Where is it?" answered before they have to ask.

Open the live demo →

MEASURE, THEN IMPROVE

Run the desk by the numbers — and let the engine improve it.

Intake and decisions are only half of it. ServiceOrbit also measures the operation and proposes its own improvements — costed, and governed. Both views below are from the live demo.

ServiceOrbit Dashboard — a service-desk operations view with a Business Impact band (staff hours saved, zero-touch at intake, AI acceptance, self-service share) plus open backlog, SLA breached, SLA attainment, median decision time, SLA-health and 14-day throughput charts.
Dashboard — live operations and business impact in one view: staff-hours saved, AI acceptance, self-service share, SLA attainment, backlog, and 14-day throughput. The numbers shown come from the demo dataset; on a real desk they're your own.
ServiceOrbit continuous improvement — 'What the engine wants to improve': AI-detected signals turned into costed proposals (auto-approve clean low-value reimbursements, fix an SLA breach trend, merge duplicate services) each with savings, risk, and accept-as-governed-change controls.
Improve — the engine watches demand, SLA, cost, and decline reasons across every live service and turns what it sees into concrete, costed proposals — auto-approve a clean low-value path, fix an SLA trend, merge duplicate services. Accept one and it becomes a governed change.

THE SERVICE ENGINE · THE DIFFERENTIATOR

It writes its own catalogue.

Most service desks make you author every service by hand. ServiceOrbit reads a department's real documents and drafts a governed Standard Service Definition — policy, eligibility, evidence checklist, routing. Approve and publish, and the live assistant starts serving it the same minute.

  • Onboard from documents — upload a real PDF/DOCX; the engine authors the service.
  • Govern it — review the policy, eligibility criteria, and routing before anything goes live.
  • Publish to D1 — the chat, voice, and email channels start serving it instantly.
  • Improve it — costed CSI proposals per service, grounded in real demand.
ServiceOrbit Service Engine — the 'Onboard a service from its documents' screen: drop a department's SOP, policy and request form, and the engine authors a governed Standard Service Definition against an 11-section template, ready to publish.

Onboard → Author → Publish

Drop a department's real PDFs; the engine drafts a governed service against an 11-section template, then you approve & publish. The flagship demo tenant ships 9 hand-scripted services + 52 AI-authored services live in the serving catalogue.

THE GOVERNED STANDARD

Every service follows one lifecycle, one definition.

Behind the catalogue is a governed standard: each service moves through propose → author → govern → publish → operate → improve → retire, and conforms to one 11-section Standard Service Definition. From the live demo.

ServiceOrbit catalogue lifecycle and standard — a nine-stage service lifecycle (propose & ingest, AI author, design fulfilment, govern & approve, publish & activate, operate & monitor, improve, change & re-version, retire) where each service conforms to an 11-section Standard Service Definition.
Catalogue lifecycle — every service is proposed, AI-authored into an 11-section Standard Service Definition, governed and approved, published live, operated, improved, re-versioned, and eventually retired. The AI drafts at each step; humans keep the gates.

THE WORKSPACE

What approvers and requesters actually open.

The channels are how requests come in. These are the surfaces where the work gets decided, tracked, and improved.

Workspace Approver

Console

AI-drafted tickets, traced evidence, a persisted AI recommendation, and one-click decisions.

Workspace Approver

Dashboard

Live ops — backlog, SLA attainment, throughput, and a business-impact (ROI) band.

Workspace Requester

Track

An SLA ring, stage progress, and proactive AI updates on where the request stands.

Workspace Everyone

Lifecycle

An orchestration map of all eight stages — where AI runs vs. where humans keep judgement.

Service Engine Approver

Catalogue

The control plane that authors, governs, improves, and retires the services the channels serve.

Service Engine Approver

Improve

Generates real, costed continual-improvement (CSI) proposals per service — grounded in live demand.

DECISIONS, NOT DATA ENTRY

Approvers decide. The engine did the legwork.

By the time a request reaches a person, it's already a clean ticket: evidence parsed, eligibility checked criterion by criterion, and a recommendation judged against the real policy. The approver reads, sanity-checks, and clicks — minutes of judgement instead of hours of triage.

A manager reviewing a request on screen with a thoughtful expression, making a decision.
ServiceOrbit · approver console

MULTI-TENANT BY DESIGN

One platform, many desks.

The same engine re-skins its brand, accounts, catalogue, and AI framing per client. Tickets, metrics, and demo resets are tenant-scoped — one client's queue never touches another's.

KU

Knowledge Unit

Higher education

Flagship — 9 scripted services + 52 AI-authored services live in the serving catalogue.

VG

Vantage Group

Corporate shared services

Internal request management across a multi-department enterprise.

NB

Northwind Bank

Banking

Policy-heavy intake with strict eligibility and evidence checks.

MH

Meridian Health

Healthcare

Sensitive workflows with human judgement kept firmly in the loop.

CS

Civic Services Authority

Government

Citizen-facing service requests with full audit and traceability.

Switch tenants from the login screen or the header — each one a fully separate desk on shared infrastructure.

See them in the demo

TRY IT TWO WAYS

Demo mode is real. Live mode is really live.

The public demo runs fully-scripted scenarios with animated cascades on every channel — no key needed, nothing to break. Flip to Live mode and the same flows run on real model calls: conversational intake, document parsing, approver assessments, and service authoring.

Demo mode · default

Scripted scenarios, animated channel cascades, presenter script. Explore freely with no sign-up.

Live mode · real AI

Real model calls for intake, vision parsing, approver assessment, and authoring. Gated behind an unlock — it fails safe when locked.

HOW IT'S BUILT

Edge-native, and honest about the model.

Cloudflare Workers + D1

Next.js on the edge via OpenNext; serverless SQLite for tickets, events, and the published catalogue.

In-memory document parsing

Uploads are parsed in memory; only the extracted fields persist, and the raw files are discarded.

Zero-retention model calls

The LLMs ServiceOrbit calls operate under zero-retention API terms. We never train on your content.

Geofence-ready egress

An optional proxy routes model traffic for regions that geoblock OpenAI — Workers run near your users.

Same data commitments as the rest of Dendrites AI — see our data practices.

SEE IT FOR YOURSELF

Walk a request from words to done.

Open the live demo, pick a tenant, and watch a plain-language request become a validated, routed ticket across chat, voice, and email.