Skip to content
Intelina VoiceIntelina Desk

AI that answers the phone and the chat window.

Intelina runs your customer conversations across both channels — a speech-to-speech voice agent with a customer CRM behind it, and an embeddable chat agent with a full ticketing workspace. Same knowledge, same tenant isolation, same controls.

Intelina Voice1:12on call
Recordingμ-law 8 kHz
  • 0:04CallerHi, I want to check my claim status.
  • 0:09AgentHi Mike — your claim CLM-4821 is approved.
  • 0:21CallerCan you file a new one for $500?
  • 0:29AgentDone — claim CLM-4822 is filed. I've texted you the reference.
tool · file_claimCLM-4822 createdlogged to call history
Intelina Desk0:48chatting

Why was I charged twice this month?

I see two charges on your Pro plan. The second was a failed retry — it will drop off in 3 days.

I'd rather talk to someone.

Escalated · ticket #2041 assigned
Support agent

Thanks for waiting — I've refunded the duplicate charge. Nothing else you need to do.

endpoint · billing_historyescalated to agentticket #2041 · thread attached
Two modules

Pick the channel that hurts. Add the other when you're ready.

Voice and Desk are separate products with their own dashboards, their own data model and their own pricing. They share the retrieval layer, the tenancy model and the security controls underneath.

Module 01

Intelina Voice

Phone

AI voice agents + customer CRM

Give every inbound phone line a speech-to-speech agent that knows the caller, answers from your own knowledge base, and takes real actions in your systems mid-call — with the customer records, transcripts and call history kept in one place.

Speech-to-speech
Full duplex
Audio bridge
μ-law ⇄ Opus
Knowledge freshness
< 60s
  • Real-time speech-to-speech — Caller audio goes straight into a speech model that speaks back — no relay of transcribe, think, then read aloud, so turn-taking and interruptions feel like a phone call, not a bot.
  • The agent knows who called — Before the first word, the caller's phone number is resolved against your customer records and the name, plan, balance and policy are already in the agent's context.
  • Grounded in your documents — Upload PDFs, DOCX or TXT. They're chunked, embedded and indexed per organisation, then retrieved as the caller asks domain questions — with strict tenant isolation and no cross-tenant fallback.
  • Tools you define, not us — Describe a tool in the dashboard — an HTTP webhook into your CRM, a customer lookup, an escalation, an end-of-call action — and the agent can call it. No redeploy, live within about a minute.
Module 02

Intelina Desk

Web chat

AI chat + ticketing tool

One script tag puts an AI support agent on your site. It recognises the signed-in user, answers from your live APIs and your knowledge base, and opens a ticket with a human the moment it is out of its depth — with the full agent, supervisor and admin workspace behind it.

Time to install
1 script tag
Customer data stored
None at rest
Handoff
Context intact
  • Embed in one line — A single script tag, themed to your brand colour, logo and screen position. It renders on your site without touching your build.
  • Knows the signed-in user — The widget calls an endpoint on your own domain with the user's session cookie, so the bot greets them by name and answers personally from the first message.
  • Live data, not stale copies — Register your APIs as tools — wallet balance, orders, subscription plan. The AI decides when to call them and reads the answer back. Nothing is copied into our database.
  • You choose what the AI can see — Each endpoint carries a field whitelist, so only the exact fields you name are ever passed into the model. Everything else is dropped before it leaves your API.
Shared foundation

Two front doors, one engine room.

Whichever module you start with, the knowledge, connectors, tenancy and governance underneath are the same. Adding the second channel is configuration, not a second integration project.

Intelina Voice

AI voice agents + customer CRM

Intelina Desk

AI chat + ticketing tool

Shared platform layer
Knowledge retrieval·Live connectors·Tenant isolation·RBAC + audit·Encrypted secrets·Containerised runtime

One retrieval layer

Both modules index documents into the same search layer, partitioned by tenant. Upload once, ground answers on the phone and in chat.

Your systems, called live

Voice tools and chat data endpoints are the same idea in two channels: you register an API, the AI decides when to call it, and the response comes back fresh.

Multi-tenant to the row

Every query, cache key, search filter and API key is scoped to an organisation or project. There is no unfiltered fallback path in either module.

Governed by default

Role-based access, audit logging, encrypted secrets and per-key scoping ship with the platform rather than as an enterprise add-on.

Containers you can host

Every service is a container. Run it on our managed cloud or inside your own — the deployment topology is the same either way.

Adopt one, add the other

The modules are independent products with their own dashboards. Start with the channel that hurts most and turn the second one on later.

Runtime

What actually happens between the question and the answer.

No hand-waving: this is the sequence each module runs, in order, on every conversation.

What happens when the phone rings

  1. 01

    Call arrives

    The telephony provider posts the dialled number to the orchestrator, which resolves it to your organisation.

  2. 02

    Context assembled

    Agent persona, the caller's customer record and the relevant knowledge chunks are fetched in parallel and composed into one prompt.

  3. 03

    Agent connects

    The speech model opens with your persona, voice and the caller's real data already loaded.

  4. 04

    Conversation runs

    Audio is bridged both ways while transcripts are scanned for actionable intent.

  5. 05

    Actions execute

    A detected intent dispatches your tool, and the result is folded back into the agent's context.

  6. 06

    Call closes

    Remaining actions run, the transcript and recording are logged, and the caller receives an SMS confirmation.

Security

Built for teams whose legal team asks questions.

Both modules ship the same posture: minimal data retention, explicit field-level control over what the model sees, hardened outbound calls and an audit trail that records who touched what.

Data handling

  • Live customer data is fetched on demand and held in a short-lived in-memory cache — never written to a database
  • Per-endpoint field whitelists control exactly which fields reach the model
  • Integration credentials are encrypted at rest and only their names appear in admin responses
  • Call recordings and transcripts are stored against your organisation and nobody else's

Access control

  • Role hierarchy from super admin down to support agent, enforced per request
  • Optional TOTP two-factor authentication for staff accounts
  • Short-lived access tokens with an explicit token type claim, so a refresh token cannot act as an access token
  • Service API keys can be bound to a single organisation, and cross-tenant calls are rejected

Network posture

  • HTTPS required for every registered outbound endpoint
  • Private, loopback, link-local and reserved IP ranges rejected before a request is made
  • The resolved address is re-validated at connection time, closing DNS-rebinding windows
  • Redirects disabled on outbound calls, with per-IP and per-route rate limiting

Accountability

  • Admin operations, data fetches, logins and escalations recorded with actor, action and entity
  • Audit entries carry metadata only — response payloads are never stored
  • Mutating agent actions are deduplicated so a retry cannot double-charge or double-file
  • Every call and every ticket keeps the exact context the AI was given

How these controls map to common frameworks

These are the platform capabilities relevant to each framework, not a claim of certification. Ask us for the current attestation status during your review.

GDPR

Data minimisation, on-demand fetch instead of storage, full audit trail

SOC 2

Access controls, audit logging, encryption in transit

PCI DSS

No payment data stored; tokenised access only

HIPAA

Role-based access, audit logging, tenant data isolation

Industries

What this looks like in your vertical.

The same two modules, pointed at the conversations that actually fill your queues.

Healthcare

Automate 80%+ of Patient Support Calls

Voice
Appointment booking, prescription refills and triage routing on the phone line, with the caller identified before they speak.
Desk
Portal chat for coverage questions, form help and pre-visit instructions — escalating to a coordinator as a tracked ticket.
Read the healthcare breakdown
Financial Services

Handle 15K+ Daily Account Inquiries Autonomously

Voice
Balance, transaction and card actions over the phone, with identity verified before any account data is read out.
Desk
In-app chat answering statement and fee questions from live account APIs, with disputes raised as tickets for a human.
Read the financial services breakdown
E-Commerce

Scale to 50K+ Calls During Peak Season

Voice
Order tracking, returns and delivery changes on the phone through peak season without seasonal hiring.
Desk
Storefront widget answering 'where is my order' from your OMS in real time, opening a ticket only for exceptions.
Read the e-commerce breakdown
Insurance

Reduce Claims Inquiry Time from 8 min to <1 min

Voice
Claim status, policy questions and first notice of loss captured on the call, with the claim filed before hang-up.
Desk
Policyholder portal chat for document requests and coverage lookups, routing complex claims to an adjuster with full context.
Read the insurance breakdown
Telecommunications

Resolve 80%+ of Tech Support Without Escalation

Voice
Guided troubleshooting and automated service restoration on the line, escalating only genuine hard faults.
Desk
Account chat handling billing explanations and plan changes, with the diagnostic trail attached when tier-2 takes over.
Read the telecommunications breakdown
View all industries
Pricing

Priced per module, because you buy them separately.

Voice is priced against call volume. Desk runs from $0 to $199 a month depending on seats and volume. Take one or both.

Intelina Voice

AI voice agents + customer CRM

Monthly plans by call volume

  • Starter500 calls / month$499/mo
  • Growth1,000 calls / month$799/mo
  • BusinessPopular2,500 calls / month$1,199/mo
  • Scale5,000 calls / month$1,999/mo
  • Enterprise10,000+ calls / month$3,499/mo
  • Speech-to-speech voice agent
  • Customer records and CSV import
  • Knowledge base with retrieval
  • Dashboard-defined agent tools
  • Call logs, transcripts and recordings
  • Encrypted integration secrets

Intelina Desk

AI chat + ticketing tool

Free tier, then monthly plans by team size

  • Free1 team seat$0/mo
  • Starter5 team seats$59/mo
  • ProPopularUnlimited team seats$79/mo
  • EnterpriseUnlimited team seats$199/mo
  • Embeddable AI chat widget
  • Knowledge base with retrieval
  • Live data endpoints
  • Ticketing, queues and SLA tracking
  • Agent, supervisor and admin roles
  • Analytics, audit log and webhooks

Paid plans unlock higher volumes, more agent seats and the full governance suite — approvals, audit log, webhooks and API keys.

Questions

The things people ask before the demo.

No. Voice and Desk are separate products with separate dashboards. Most teams start with whichever channel is generating the most repetitive work and add the second later. Knowledge you upload for one can be reused by the other.

Put both channels on the same brain.

Bring one line or one chat widget. We will show you the same agent answering with your real data, calling your real systems, and handing off cleanly when it should.