Skip to content
EN
Demo
Platform
CallsQueues and routingIVR (phone menu)Smart transferAuto dialerBrowser-based softphoneClick-to-call
Messaging and customer dataUnified inboxForm builderCustomer portalCustomer success platform
ManagementHistorical reportingReal-time monitoringShift scheduling
Deployment and securityIn our cloudOn your serversHybrid deploymentData security
Platform →
Solutions
IndustriesRetailReal estateBanking and insuranceTravelHealthcareEducation
Customer serviceFAQ self-serviceOrder status without an agentAfter-hours coveragePeak days without overloadConversation quality assurance
SalesLead qualificationAppointment bookingRepeat salesLoyalty program
Outbound communicationPayment and overdue remindersNotifications and confirmationsPost-interaction survey
Who it's forBy company sizeBy role
Solutions →
AI agents
For customersVoice AI consultantAI consultant in chat
For employeesAI assistant for calls and salesAssistant for work questionsNew hire onboarding
TechnologyKnowledge baseSpeech analyticsAI connectorModelsData security
ServicesAI agent trainingMachine learning
AI agents →
Integrations
CRM systemsSalesforceHubSpotDynamics CRMSAP CXZoho CRMPipedrive
ERP systemsSAPNetSuiteBusiness CentralSageOdoo
Help desk and team chatZendeskFreshdeskServiceNowSlackMattermost
Messaging and socialWhatsAppViberInstagramFacebookSMSLive chat
Telephony, API, and AIAsteriskAMI, AGI, and ARIKamailioFreeSWITCHAPI and protocolsMCP connectors
Integrations →
Pricing
Company
ResourcesBlogCalculatorsComparisonsLibraryGlossary
ServicesOpen SourceImplementationDevelopmentSupportTraining
ContactsContact usAboutFacts and figures
Company →
Language: English
Demo

Use cases

Answers to common questions, no agent needed

With CONTACT.WORK, AI agents handle routine questions – business hours, prices, terms, order status. Customers get an answer instantly, even at night: on the phone from the IVR or a voice AI agent, and in chat from the AI consultant, which replies in text. They all answer from the same company knowledge base, so the answers match everywhere. If the knowledge base has no answer, the AI agent hands the whole conversation to an employee, and your agents spend their shifts on sales and complex inquiries.

Get a quotePricing
24/7answers for customersBy voice and text
1knowledge baseFor AI agents and employees
2types of AI agentVoice and text
$0for the knowledge basePart of the platform

Challenges

What routine questions cost you without automation

Repeating the same thing all dayAgents read out business hours and addresses over and over while complex calls wait their turn.
Long waits for small questionsTo find out a delivery fee, the customer has to sit through hold music.
Inconsistent answersChat says one thing, the phone line says another, and the customer stops trusting both.
Knowledge lives in people's headsOnly experienced agents know the right answer, while new hires get confused and have to ask.
No one there in the eveningA question asked after 6 PM sits unanswered until morning.
No one is countingYou don't know which questions are most common or which ones the knowledge base can't answer.

Solution

Your contact center after implementation

Voice

Agents take only the calls that need them

The IVR recognizes why the customer is calling and immediately gives business hours, an account balance, or order status. It pulls the data via API from your CRM, ERP, or billing system. For harder questions, customers ask the voice AI consultant in their own words instead of navigating menu branches.

  • Data-driven IVR
  • Voice answers
  • Natural speech

Messaging

Messages don't pile up while agents are on calls

The text AI agent handles conversations in your website chat, messaging apps, and email, transcribes voice messages, and takes into account which page of your website the customer is on. If the customer goes quiet, it follows up automatically.

  • Website, messaging, email
  • Voice messages
  • Follow-up

Knowledge base

One edit updates every channel

The IVR, AI agents, and employees all rely on a shared knowledge base. Employees see an edited answer immediately; AI agents see it after retraining, which takes longer the more you change. Each topic has an assigned owner.

  • Shared knowledge base
  • Topic owner
  • Retraining

Handoff

A person resolves complex questions, and the customer doesn't have to repeat themselves

When the knowledge base doesn't have the answer, the AI agent doesn't make one up – it transfers the customer to an employee. The employee immediately sees the conversation and customer details, so there's no need to ask again.

  • No made-up answers
  • Conversation on screen
  • Customer details

Reporting

See what to add so AI resolves more

A report shows the most popular menu options, where callers hang up, and how many inquiries were resolved without staff. Everything left unanswered goes into a list of knowledge base gaps.

  • Containment rate
  • Drop-off points
  • Gaps to fill

Examples

Four common questions

The customer's situation and the result for your business.

A call after closing

Around 11 PM, a customer calls your company to find out what time the nearest branch opens tomorrow and where to park. Before, this call went nowhere, and in the morning a manager worked through the missed-call list. Now the IVR tells the caller when the nearest branch opens and where it is, and the voice AI consultant answers the parking question. The customer gets an answer right away, and the manager starts the morning with one less task.

  • After hours
  • Nearest branch
  • No morning callbacks
Example 1 of 4

These use cases are examples: you decide which topics to hand to AI agents.

Features

What else AI agents can handle

Routine answers, customer data, convenience, and oversight.

Routine answers

  • DocumentsWhich documents to bring to an appointment, a closing, or an order pickup.
  • Payment optionsHow and where to pay for an order or service, and what payment details to use.
  • Warranty and cancellationWarranty periods and terms for canceling an order or rescheduling a visit.
  • DeliveryDelivery times and areas, and the address of the nearest pickup point.

Customer data

  • Reward pointsThe customer's loyalty program balance.
  • AppointmentsWhen the customer is booked and how to reschedule.
  • Balance dueThe amount and date of the next payment, based on your accounting data.
  • Identity verificationConfirms the caller is the account holder before any questions about money.
  • Voice biometricscustomized for youThe AI agent recognizes the customer by voice, so no passcode is needed.
  • By nameThe AI agent greets the customer by name, then lists what's in their order.

Customer convenience

  • Links without pausing the callThe IVR sends a form, instructions, or a payment page by SMS or a messaging app while the conversation continues.
  • Suggested answers in formsWhile the customer fills out a contact form, matching answers from the knowledge base appear alongside it.
  • Personalized IVRIf the caller has an open order, the IVR offers its status first.
  • Customer's languageKnowledge base answers are translated into the language the customer writes in – no separate knowledge base for each language.

Oversight

  • Restricted sectionsInternal policies are visible only to employees with the right permissions.
  • Answer sourceThe AI agent cites the knowledge base article it used, so the answer is easy to verify.
  • Watching AI agents liveA supervisor sees AI agent conversations as they happen and can step in when needed.
  • Website searchA report shows what customers search for in the help section of your website and which searches return nothing.
  • Suggestions from employeesAn agent flags an inaccurate answer and suggests a fix, and the topic owner accepts or rejects it.

Modules

Contact center modules

IVR (phone menu)Gives customers business hours, account balances, and order status from your systems. Routes all other calls to an agent or an AI agent.→Voice AI consultantUnderstands questions asked in natural speech and answers by voice from the knowledge base. Transfers complex cases to an employee.→AI consultant for chatAnswers in your website chat, messaging apps, and email around the clock. Responds instantly, even while agents are on calls.→Knowledge baseOne shared knowledge base for the IVR, AI agents, and people, at no extra charge. Each topic has an assigned owner.→AI agent trainingEach new AI agent version is first tested on real inquiries from your customers. It goes live only if it answers more accurately than the previous one.→OmnichannelA customer's calls and chats appear in order, from the very first contact. When an AI agent transfers a conversation, the employee knows the whole history.→
Agent time goes to salesAI agents handle routine questions so your team doesn't repeat them all day. Less repetitive work means lower turnover, and people focus on disputes, complaints, and sales.
Customers don't waitCustomers get an answer right away, at any hour, with no hold music. A simple question no longer waits while agents work through complex inquiries.
One answer in every channelThe IVR, both AI agents, and your team answer from the same knowledge base section. Customers hear on the phone exactly what they read in chat, and they trust you more.
Grow the knowledge base by the numbersA report counts inquiries resolved by AI agents and collects questions left unanswered. You add to the knowledge base based on data, not guesswork.

Launch

How we launch

  1. 01AssessmentWe find the questions that take up the most agent time – that's where AI agents start paying off.
  2. 02Knowledge baseWe build the first sections from your instructions, documents, and website, and assign topic owners.
  3. 03IVRWe move common questions into the IVR and connect it to orders, balances, and appointments from any of your systems.
  4. 04AI agentsWe train both AI consultants – voice and text – to answer from the knowledge base and hand complex cases to people.
  5. 05TestingBefore launch, we test the AI agents on real questions from your customers and fix inaccurate answers.
  6. 06Go-liveWe launch channels one at a time and use reports to show how many inquiries are already resolved without staff.

Preparation

What to decide in advance

Which questions come first?Pick questions you get every day that don't need a person to decide – we'll start there.
Where do the answers live now?Gather your instructions, policies, and website copy – we'll build the first knowledge base sections from them.
Who will own each topic?Assign one employee per topic to edit answers and fill in whatever the knowledge base is missing.
What goes straight to people?List the topics only people should handle – disputes, refunds, complaints – and the AI agent will transfer them right away.
What data should customers get?Decide what customers can look up from your systems – orders, balances, appointments – and we'll connect the platform to those systems.

Q&A

Frequently asked questions

Which questions can AI agents handle?

The ones you get all the time: business hours, locations, prices, return and warranty terms. When your systems are connected to the platform, the AI agent can also tell customers where their order is, what their account balance is, or when their appointment is.

Do we have to write the knowledge base from scratch?

You don't: we build the first sections from the instructions, policies, and website copy you already have.

Is the knowledge base an extra cost?

No, the knowledge base comes with the platform. Migrating your content and configuring it are billed as support hours on your plan.

Pricing calculator →

How much do AI agents cost to run?

In our cloud, the voice AI agent starts at $0.06 per minute of conversation; on your own servers there's no per-minute charge. The text AI agent is priced separately, based on the language model and AI service you pick.

Pricing calculator →

How long does launch take?

In the cloud, an AI agent can be switched on in as little as a day. What takes longer is gathering answers for the knowledge base and testing on your customers' questions. Our engineers' time comes out of your plan's support hours.

How do we know the AI agent is doing its job?

Check the report: how many questions were resolved without people, where callers drop out of the IVR, and what the knowledge base can't answer yet. Look at the containment rate together with customer ratings – that shows whether the AI agent actually helped or the conversation just ended.

How do we calculate the savings?

Multiply the number of inquiries resolved without staff by the time an agent used to spend on each. That gives you the hours freed up on your phone lines. The calculator helps estimate annual savings.

Savings calculator →

Can the AI agent handle a seasonal spike in calls?

How many conversations it handles at once depends on server capacity and the number of phone lines, which are sized for your peak. On those days, the AI agent takes routine questions, so fewer calls reach your agents.

Who keeps the AI agent's answers up to date?

An assigned employee maintains the knowledge base themselves, with no developers needed. Our engineers reconfigure the IVR at a manager's request, using your paid support hours.

Can we show knowledge base answers on our website?

With widgets and the API, you can show answers on the pages you choose, so customers find them on their own without contacting you.

Do we need to copy content from Confluence or our website into the knowledge base?

Not necessarily: answers can come from documents in your internal systems, such as Confluence or SharePoint, and from your website pages – no need to move them.

How do we know if an answer helped?

After answering, the AI agent asks whether it was helpful. Low-rated answers are collected separately, and the topic owner rewrites them.

When do we need a voice AI agent, and when is an IVR enough?

The voice AI consultant is available for contact centers with 10 agents or more. Smaller teams usually get by with a touch-tone IVR, and a text AI agent can cover messaging.

Glossary

Terms on this page

Knowledge base
All answers, policies, and prices in one place – for agents and AI. Learn more →
IVR (interactive voice response)
A phone menu: the caller hears a greeting and picks the right department. Learn more →
API (application programming interface)
The way programs exchange data with each other without a person in the loop. Learn more →
Cloud deployment (cloud)
The platform runs on the vendor's servers, and agents connect over the internet. Learn more →
CRM – customer relationship management
Where a company keeps its customers, deals, and full communication history. Learn more →
ERP – enterprise resource planning
Orders, inventory, and finance in one system. Learn more →
Callback
The customer doesn't wait on hold but asks for a callback – and gets one when an agent is free. Learn more →
Supervisor
Leads a team of agents: watches the queue and quality, helps and coaches. Learn more →
Omnichannel customer service
All channels in one agent workspace, with the customer's full history alongside. Learn more →
On-premises deployment
The system runs on the company's own servers, not in the vendor's cloud. Learn more →
Large language model (LLM)
A neural network that understands questions asked in everyday words and answers the same way. Learn more →

More

Related reading

After-hours answering How to run your contact center after the office closes: who answers customers at night and how to handle inquiries that come in overnight. Learn more API and protocols How to connect your CRM, ERP, or billing system so the IVR and AI agent can give customers order status and balances. We connect via REST, webhooks, or SQL. Learn more Missed call callback A customer hangs up before getting through – the system calls them back as soon as an agent in the right queue is free. No question gets lost. Learn more AI agent savings Estimate what share of inquiries an AI agent can take on and how many paid agent hours you free up – a yearly estimate based on your inquiry volume. Learn more

Blog

Fresh from the blog

All articles →
Services · 7 min read Custom development of your contact center platform for your processes When contact center settings are not enough: integrations, modules, AI workflows. How to tell development from configuration and estimate the payback. Read the article → Management · 9 min read How many agents does your contact center need? Erlang C in plain English Calculate contact center staffing with Erlang C: workload, service level, shrinkage, and headcount by shift – all in one worked example. Read the article → Integrations · 7 min read CRM and phone system integration: what it does and how it works How to connect your phone system to your CRM: calls and recordings in the record, screen pop, click-to-call. What to decide first and how to check it works. Read the article →

Updated: