# Agent Channels and Surfaces

Channels are the surfaces where an agent meets the people it works with: a chat widget on a website, a shared inbox, a Slack or Microsoft Teams workspace, a WhatsApp or Telegram thread, an SMS number, a phone line, a calendar, a meeting. The agent's reasoning can be identical across all of them, yet each surface imposes its own rules about identity, formatting, timing, attachments, and how long a conversation is allowed to stay open.

This is where most integration effort actually goes. A capable agent that lives in only one window makes people come to it, while a well routed one shows up where the work already happens. For builders, the channel layer is a translation problem plus a state problem. For buyers, it is worth checking which surfaces are genuinely supported end to end, because pushing a message into a platform is far easier than holding a coherent thread inside it.

## Start here

1. [Conversational AI](/en/glossary/conversational-ai)
2. [Conversation Thread](/en/glossary/conversation-thread)
3. [Turn](/en/glossary/turn)
4. [Channel Routing](/en/glossary/channel-routing)
5. [Chat Widget](/en/glossary/chat-widget)
6. [Voice Agent](/en/glossary/voice-agent)
7. [Omnichannel](/en/glossary/omnichannel)

## One brain, many surfaces

The durable idea in this category is separating the conversation from the transport. A thread holds the state: who is involved, what has been said, what is still open. A turn is one exchange inside it. Channel routing decides which surface a given thread reaches, and omnichannel is the property of keeping one thread coherent as it moves between surfaces, which is much harder than supporting several surfaces separately. Everything else is adaptation. Text channels differ mainly in formatting, identity and platform rules. Voice channels add a real time constraint, because recognition, model response and synthesis all have to fit inside the pause a person will tolerate.

## Voice is a different engineering problem

Text channels forgive delay and voice does not. A spoken exchange chains speech to text, a model response and text to speech, and the sum of those steps is what a caller experiences as awkward silence. That is why voice latency gets tracked separately from ordinary response time, and why streaming partial output matters more here than anywhere else. Barge in, letting a person interrupt mid sentence, is not a nicety but the difference between a conversation and a recording. Telephony integration adds carrier concerns, and older interactive voice response menus are the experience most callers are silently comparing you against.

## What people get wrong

The frequent mistake is treating each channel as a separate product, which produces an agent that knows a customer in email and not in chat. Thread identity should be resolved before surfaces multiply. A second is assuming asynchronous surfaces behave like chat: email arrives in unpredictable shapes with quoted history and attachments, so parsing is real work, and replies are expected to read like email rather than chat output. A third is underestimating platform constraints, since messaging platforms carry their own approval processes, template rules and session windows that shape what you may send and when. Finally, voice gets judged on timing and interruption handling long before content.

## Commonly confused

### Chatbot vs Conversational AI

Chatbot usually implies scripted or menu driven flows, while conversational AI describes open ended dialogue, though marketing uses the two interchangeably.

### Barge In vs Voice Latency

Barge in is whether a caller can interrupt the agent mid sentence, while voice latency is how long the caller waits before a reply begins.

### Voice Agent vs Interactive Voice Response

Interactive voice response walks callers through predetermined menus, while a voice agent holds an open conversation and decides what to do next.

### Omnichannel vs Channel Routing

Routing picks which surface a message goes to, while omnichannel is the harder property of keeping one continuous thread as a person moves between surfaces.

## Every term in Agent Channels and Surfaces

- [Adaptive Card](/en/glossary/adaptive-card): Adaptive Cards are an open card exchange format, originated by Microsoft, in which content and layout are described in JSON and rendered natively by whichever host application receives them. The same payload can appear in different hosts, each applying its own styling. They are widely used for interactive messages and dialogs in Microsoft Teams and related surfaces.
- [App Home](/en/glossary/app-home): App Home is a dedicated per-application space inside a chat platform, most prominently in Slack, where an installed app presents its own persistent view to an individual user. It typically combines a direct message conversation with the app and a rendered tab that the app publishes and updates. It gives a chat-installed app a stable place to live beyond message history.
- [Barge In](/en/glossary/barge-in): Barge in is the ability of a voice system to let a speaker interrupt while it is talking, stopping its own audio and processing what was said. Without it, callers must wait for a prompt to finish before responding. Supporting barge in requires detecting genuine speech during playback and separating it from the system's own audio echo.
- [Business Hours Routing](/en/glossary/business-hours-routing): Business hours routing sends an incoming contact down a different path depending on the time it arrives, evaluated against a defined schedule. Inside published hours it follows the normal flow; outside them it reaches an alternative such as an asynchronous handler, a message capture, or a booked callback. The schedule carries time zones, holidays, and exceptions.
- [Calendar Integration](/en/glossary/calendar-integration): Calendar integration is the connection between an application and a calendar service so it can read events, check availability, and create or update bookings. It uses provider APIs or open standards, with authorization granted by the calendar owner. For an assistant, the calendar is both a source of context and the place where scheduling decisions are recorded.
- [Call Deflection](/en/glossary/call-deflection): Call deflection is the practice of offering an inbound caller an alternative route to resolution, such as a text conversation, a self-service link, or a scheduled callback, instead of continuing to hold on the line. The caller chooses whether to accept. Deflection is measured by resolution on the alternative path, not simply by calls leaving the queue.
- [Callback Scheduling](/en/glossary/callback-scheduling): Callback scheduling lets an inbound caller hang up while keeping their position in a queue, then receive a return call when their turn arrives or at a time they choose. The queue continues to advance in the caller's absence. It exists in two forms: an immediate virtual queue callback and a booked callback at a future slot.
- [Canned Response](/en/glossary/canned-response): A canned response is a stored, reusable message that can be inserted into a conversation instead of being written from scratch. Most implementations support placeholders that fill in details such as a name, order number, or link at insertion time. They are also called saved replies or macros, and macros often bundle actions alongside the text.
- [Channel Routing](/en/glossary/channel-routing): Channel routing is the logic that decides where an inbound message or call goes and which path the reply returns on. Rules can consider the channel it arrived on, the content of the request, the customer's identity or value, language, working hours, and current load. Routing also covers escalation, when a conversation is handed to a different handler.
- [Chat Widget](/en/glossary/chat-widget): A chat widget is the embeddable chat interface that appears on a website or in an application, usually as a launcher button in a corner that opens a conversation panel. It is delivered by a small script or an inline frame and connects the page to a messaging backend. The widget is the presentation layer, separate from whatever answers the messages.
- [Chatbot](/en/glossary/chatbot): A chatbot is a software application that holds a text conversation with a person through a messaging interface. Implementations range from rule based systems that match keywords to scripted replies, through to systems driven by large language models that generate each response. The word describes the interface and product form, not any particular underlying technology.
- [Co-Browsing](/en/glossary/co-browsing): Co-browsing is a session in which a helper views, and sometimes interacts with, the same web page a visitor is on, scoped to that page rather than the visitor's whole device. Implementations either mirror the page structure to reconstruct it remotely or stream pixels of the page region. Field masking is a standard requirement so sensitive values never leave the visitor's browser.
- [Conversation Thread](/en/glossary/conversation-thread): A conversation thread is the ordered sequence of messages that belong to a single exchange, together with the identifiers that keep them grouped. Threads give an assistant the history it needs to interpret references such as 'that one' or 'the second option.' Platforms implement threading differently, from email headers to explicit thread objects in chat systems.
- [Conversational AI](/en/glossary/conversational-ai): Conversational AI is the field of software that interprets human language input and responds in natural language across text or speech. It covers the components that make dialogue work, including language understanding, dialogue management, response generation, and, for voice, speech recognition and synthesis. The term describes a capability rather than a single product or architecture.
- [Deep Link](/en/glossary/deep-link): A deep link is a URL that opens a specific location inside an application rather than its default entry screen. Implementations range from custom URL schemes to verified web links that open the app when installed and the website otherwise. Deep links are how a conversation hands the user to the exact record, screen, or thread being discussed.
- [DTMF](/en/glossary/dtmf): DTMF, short for dual-tone multi-frequency, is the signaling scheme that turns a telephone keypad press into a pair of simultaneous tones. Each key combines one tone from a low group and one from a high group, so a receiver can identify the digit unambiguously. It remains the standard way callers enter numbers and menu choices on a voice call.
- [Email Agent](/en/glossary/email-agent): An email agent is a system that monitors a mailbox, interprets incoming messages, and acts on them by replying, filing, extracting data, or triggering downstream work. It connects through a mail protocol or provider API and works within an email thread rather than a live chat session. Actions may be sent automatically or held for a person to review.
- [Embedded Assistant](/en/glossary/embedded-assistant): An embedded assistant is an assistant that lives inside a host application and has access to that application's context and actions. Unlike a general chat interface, it can read what the user is currently viewing and operate on it, for example editing a record or filtering a report. The assistant is a feature of the product it sits in.
- [Endpointing](/en/glossary/endpointing): Endpointing is the decision a voice system makes about when a speaker has finished their turn and a response should begin. It combines silence timing with acoustic and linguistic cues to separate a natural mid-sentence pause from a genuine handoff. Getting it wrong produces either interruptions or noticeable dead air.
- [Inbound Email Parsing](/en/glossary/inbound-email-parsing): Inbound email parsing is the process of turning a received email into structured data an application can use. It separates headers, the new message body from quoted history, signatures, inline images, and attachments, then usually delivers the result to an application as a webhook payload or an API object. It is the entry step for any system that acts on email.
- [Interactive Voice Response](/en/glossary/interactive-voice-response): Interactive voice response is a phone system that plays recorded or synthesized prompts and collects caller input, traditionally as keypad tones and increasingly as speech. It uses that input to route the call or to complete a simple transaction such as checking a balance. Classic interactive voice response follows a fixed decision tree defined in advance.
- [Meeting Assistant](/en/glossary/meeting-assistant): A meeting assistant is a system that joins or connects to a video or audio meeting to capture what is said and produce usable output afterward, such as a transcript, a summary, and action items. It typically joins as a participant through a calendar invitation, or connects through the conferencing platform's own recording interface.
- [Meeting Transcription](/en/glossary/meeting-transcription): Meeting transcription is the conversion of a multi speaker conversation into a written record, usually with speaker labels and timestamps. It combines speech recognition with diarization, the task of determining who spoke when, and often adds punctuation and paragraph structure. Accuracy depends on microphone setup, overlapping speech, and how familiar the vocabulary is.
- [Microsoft Teams App](/en/glossary/microsoft-teams-app): A Microsoft Teams app is a package installed into a Teams tenant that can add a conversational bot, tabs, message extensions, or interactive cards. It is described by a manifest, distributed through an organization catalog or the public store, and governed by tenant administrators. Identity and permissions come from the organization's directory.
- [Omnichannel](/en/glossary/omnichannel): Omnichannel describes an approach where every contact surface, such as chat, email, phone, and messaging apps, feeds one shared record of the customer and their history. A conversation started in one channel can continue in another without the person repeating themselves. It contrasts with multichannel, where the same channels exist but each keeps its own separate history.
- [Push Notification](/en/glossary/push-notification): A push notification is a message delivered to a device through a platform push service rather than requested by the application itself. The app registers for a token, a server sends a payload addressed to that token, and the operating system displays or delivers it even when the app is closed. Web browsers support an equivalent mechanism through their own push services.
- [Push To Talk](/en/glossary/push-to-talk): Push to talk is a voice input mode where the user holds or taps a control to mark exactly when they are speaking. The microphone captures audio only within that window, so the system never has to infer where an utterance begins or ends. It is the deterministic alternative to wake words and automatic endpointing.
- [Queue Position](/en/glossary/queue-position): Queue position is the ordinal place a waiting contact holds in a line, often announced together with an estimated wait time. Position comes directly from queue depth and ordering rules, while the estimate is derived from recent handling times and available capacity. The two are frequently confused, and only the first is exact.
- [Quick Reply](/en/glossary/quick-reply): A quick reply is a tappable suggested answer presented to the user alongside a message, usually as a row of short chips. Selecting one sends that value as the user's next message, so the conversation stays in the message stream rather than opening a separate form. Most platforms treat quick replies as transient and hide them once a choice is made.
- [Read Receipt](/en/glossary/read-receipt): A read receipt is a signal reporting that a recipient's client has displayed a message, usually shown as a status marker beside it. Platforms typically distinguish several states, such as sent, delivered to the device, and read. The read state indicates rendering on screen, which is not the same as a person having taken in the content.
- [Real-Time Transcription](/en/glossary/real-time-transcription): Real-time transcription converts speech to text continuously while a person is still speaking, emitting provisional results that are revised as more audio arrives. It differs from batch transcription, which processes a complete recording after the fact and can use the whole file as context. The live variant trades some accuracy for immediacy.
- [Rich Card](/en/glossary/rich-card): A rich card is a structured message unit combining elements such as a title, description, image, and action buttons into a single rendered block. Several cards shown in a horizontally scrollable row form a carousel. Cards let a conversational surface present selectable options and records without leaving the message stream for a separate page.
- [SIP Trunk](/en/glossary/sip-trunk): A SIP trunk is a virtual connection that carries phone calls between an organization's phone system and a voice service provider over an IP network. Session Initiation Protocol handles call setup and teardown while the audio itself travels as RTP media streams. It replaces the physical circuits that older systems used to reach the public telephone network.
- [Slack App](/en/glossary/slack-app): A Slack app is an integration installed into a Slack workspace that can post messages, respond to events, add slash commands, and render interactive surfaces. It authenticates with scoped tokens granted at install time and receives activity through the events subscription or a socket connection. Apps act under their own identity or, with permission, on a user's behalf.
- [Slash Command](/en/glossary/slash-command): A slash command is a text command typed in a chat composer, beginning with a forward slash, that invokes a registered handler instead of sending an ordinary message. The platform parses the command name and any arguments, then delivers a structured payload to the application that registered it. Responses can be private to the invoker or visible to the whole conversation.
- [SMS Agent](/en/glossary/sms-agent): An SMS agent is a system that sends and receives text messages over the mobile carrier network and responds automatically. It works through a phone number or short code supplied by a messaging provider, which delivers inbound messages to an application and relays outbound replies. Message length limits, carrier rules, and consent requirements shape what it can do.
- [Speaker Diarization](/en/glossary/speaker-diarization): Speaker diarization is the process of partitioning an audio recording by speaker, answering who spoke when without necessarily knowing who anyone is. It segments the audio, embeds each segment as a voice representation, and clusters those embeddings into anonymous speaker labels. Attaching real names to those labels is a separate step called speaker identification.
- [Speech to Text](/en/glossary/speech-to-text): Speech to text is the conversion of spoken audio into written text by an automatic speech recognition model. Systems output words along with timings and often a confidence score, and may operate on a completed recording or on a live stream. Accuracy varies with audio quality, accent, vocabulary, background noise, and how many people are speaking.
- [Telegram Bot](/en/glossary/telegram-bot): A Telegram bot is an automated account on Telegram controlled through the platform's bot API. It receives updates either by long polling or by a webhook, and replies with messages, media, inline keyboards, or files. Bots can operate in private chats, groups, and channels, and what they can see inside a group depends on their privacy setting.
- [Telephony Integration](/en/glossary/telephony-integration): Telephony integration is the connection between software and the telephone network so that a program can place calls, receive them, and control audio in real time. It typically uses a session protocol such as SIP or a provider API that abstracts it, together with phone numbers, call routing rules, and media streaming. This is the plumbing behind any automated phone line.
- [Text to Speech](/en/glossary/text-to-speech): Text to speech is the generation of spoken audio from written text. Neural synthesis models produce speech with natural rhythm and intonation, and can be steered by voice selection, speaking rate, and markup that controls pauses or emphasis. Streaming synthesis begins producing audio before the full text is ready, which matters for live conversation.
- [Turn](/en/glossary/turn): A turn is one contribution to a conversation by one party, followed by the other party's opportunity to respond. In text systems a turn is usually a single message, while in speech it is a stretch of talk bounded by the speaker yielding the floor. Counting turns is how dialogue systems measure conversation length and structure context.
- [Typing Indicator](/en/glossary/typing-indicator): A typing indicator is a transient signal shown in a conversation to convey that the other party is composing a message. It is usually sent as an ephemeral event with a short expiry, refreshed while composition continues and cleared when the message is sent or abandoned. Most platforms never store these events in the message history.
- [Voice Activity Detection](/en/glossary/voice-activity-detection): Voice activity detection is the frame-by-frame classification of an audio stream into speech and non-speech. It runs ahead of transcription and other processing so that silence, noise, and background sound can be skipped. VAD supplies the raw speech and silence signal that endpointing, barge-in handling, and bandwidth control all build on.
- [Voice Agent](/en/glossary/voice-agent): A voice agent is a system that holds a spoken conversation, converting the caller's speech to text, deciding on a response, and speaking that response back. It runs over a phone line, a web audio session, or a device microphone. Beyond answering questions, most voice agents can take actions such as booking, looking up records, or transferring the call.
- [Voice Cloning](/en/glossary/voice-cloning): Voice cloning is the creation of a synthetic voice that reproduces the timbre and speaking style of a specific person, built from recorded samples of that person. Some systems need hours of studio audio, while others approximate a voice from a short clip. The resulting voice can then read arbitrary text supplied by whoever controls it.
- [Voice Latency](/en/glossary/voice-latency): Voice latency is the delay between a speaker finishing and the system starting to respond audibly. It accumulates across the whole path: audio transport, endpointing, speech recognition, response generation, speech synthesis, and playback. Because spoken conversation has short natural gaps, latency is one of the strongest determinants of whether a voice interaction feels workable.
- [Wake Word](/en/glossary/wake-word): A wake word is a short spoken phrase that a device or application listens for in order to activate its full voice pipeline. A small always-on detector runs continuously on a local audio buffer and only opens the main recognition path once the phrase matches, which keeps compute low and limits how much audio ever leaves the device.
- [Warm Transfer](/en/glossary/warm-transfer): A warm transfer is a call handoff in which the transferring party first speaks privately with the destination, passes context, and only then connects the caller. It contrasts with a cold or blind transfer, where the call is redirected immediately with no consultation. Warm transfers preserve continuity at the cost of a longer handoff.
- [WhatsApp Business API](/en/glossary/whatsapp-business-api): The WhatsApp Business API is the programmatic interface Meta provides so businesses can send and receive WhatsApp messages at scale. Inbound messages reach the business as webhook events, and replies are sent through API calls from a verified business account with a registered phone number. It is distinct from the consumer app and from the standalone WhatsApp Business app.

[Back to the AI Glossary](/en/glossary)