Note: Register now for Alexa Live, Amazon’s annual Alexa developer conference on July 20, 2022.
Table of contents
- Alexa app
- The companion app for Alexa customers to set up devices, change settings, and see the displayed output from interactions with Alexa.
- Alexa-enabled device
- A device that provides access to the Alexa service. Examples include Amazon Echo, Amazon Echo Dot, Amazon Tap, Echo Show, and devices made by other manufacturers that use the Alexa Voice Service.
- Alexa service / Alexa
- The cloud-based voice service that powers Alexa-enabled devices made by Amazon or other manufacturers. You can give Alexa new abilities by creating your own cloud-based service that accepts requests from Alexa and returns responses.
- Alexa skill
- See Skill.
- Alexa Skills Kit
- A collection of APIs, tools, and documentation for giving Alexa new capabilities. See What is the Alexa Skills Kit?
- Alexa Presentation Language (APL)
- A composable, responsive layout language from Amazon that is used to create interactive visual experiences for Alexa. See Understand Alexa Presentation Language (APL).
- A word or phrase that refers back to something earlier in a sentence or conversation. This may be a pronoun such as
thatand other words, but anaphors can also be longer phrases. The meaning of the word or phrase comes from the context established earlier in the conversation. Contextual carryover utterances frequently include anaphors.
- See Home card or Detail card.
- cognitive load
- The total amount of mental effort being used in the working memory, or how difficult it is for a user to understand or parse the information being presented to them.
- companion app
- See Alexa app.
- When Alexa responds with a word or phrase that lets the customer know the request was understood correctly. Types of confirmation include Implicit confirmation and Explicit confirmation.
- See Interaction.
- Information that is run through visual markup language in order to display it on screen in accompaniment to the voice interaction.
- detail card
- A card displayed in the Alexa app with information about the skill and how to use it. Customers can review detail cards and enable the skills they want. You enter most of the information displayed on the detail card on the Launch Your Skill page.
- dialog errors
- When something unexpected happened in the conversation between Alexa and the customer. Types of dialogue errors include low confidence errors, timeouts/silence/no input, and false accepts. For recommendations on how to handle dialogue errors, see the section on Error messages in the Alexa Design Guide.
- A brief sound, or audible
icon,that is distinctive enough to use represent a specific event or convey other information to a customer.
- Echo app
- See Alexa app.
- error message
- The message delivered to a customer when an utterance or technical error occurs during a dialog.
- example phrase
- A phrase showing customers what they need to say to begin using your custom skill. You'll enter these phrases in the Distribution tab of the developer console. The phrases must also be included in your list of Sample utterances.
- exit command
- When the customer says a command like
stopto end the interaction.
- exit message
- The message delivered when a customer asks the skill to stop/exit or when the conversation with the skill comes to a natural end.
- explicit confirmation
- A prompt that repeats back what Alexa heard and explicitly asks the customer to confirm whether they were correct. For example,
Alexa, ask Astrology Daily for my horoscope.Alexa would respond with,
You wanted a horoscope from Astrology Daily, right?
- false accept error
- When Alexa has mid to high confidence in understanding what the customer said, but actually misunderstands and uses an utterance that doesn't match.
- full intent invocation
- A customer's request that contains all information Alexa needs to make the request actionable. For example,
Alexa, ask History Buff what happened on June 3rd.
- graphical user interface (GUI)
- A method for people to interact with and control computers and devices through visual indicators such as icons and imagery instead of using a command-line interface.
- help message
- The message delivered to a customer who either asks the skill for help or reaches an error message too many consecutive times. A high-level help message delivers information about the skill and its features that includes similar information as the first-time welcome message. Contextual help messages are delivered when the customer is trying to use a specific feature or is stuck on a certain task or prompt.
- A text string that represents an action or utterance that a customer can say while engaging with your skill.
- home card
- An element displayed in the Alexa app to describe or enhance a voice interaction with a custom skill. See Including a Card in Your Skill's Response.
- implicit confirmation (landmarking)
- A prompt that subtly repeats back what Alexa heard to give the customer assurance that they were correctly understood. In the following example, repeating back the word
horoscopeis a landmarking technique used to establish trust with the customer but still supports natural dialog.
Alexa, ask Astrology Daily for my horoscope.Alexa would then ask to clarify the request with,
Horoscope for what sign?
- A representation of the action that fulfills a customer's spoken request. Intents can have further arguments called slots that represent variable information. For example,
Alexa, ask History Buff what happened on June third.In this statement,
…what happened on June thirdmaps to a specific intent that can be handled by a particular Alexa ability. This tells Alexa that the user wants the skill History Buff to get historical information on a specific date.
For details about defining intents, see Create Intents, Utterances, and Slots.
- An exchange of information in conversational format between the user and Alexa. This may be a single request-response, or a more extended set of turns.
- When the interaction between Alexa and the customer is interrupted by another event. Examples of interruptions are alarms and timers going off while the customer is talking to Alexa.
- The act of beginning an interaction with a particular Alexa ability. For example, if a customer wants to wake Alexa to use the Horoscope skill,
Alexa, ask Horoscope for today's reading.
Alexa then follows up after the invocation and asks,
What horoscope sign would you like?
Types of invocations include: full intent invocation, partial intent invocation, and no intent invocation.
- invocation name
- A name that represents the skill that the user wants to use. The user says a supported phrase in combination with the invocation name for a skill to begin interacting with that skill. For example,
Alexa, ask History Buff what happened on June third.In this example, History Buff is the invocation name for a skill that retrieves historical events. Note that smart home skills don't have invocation names.
- See Implicit confirmation.
- A visual template which describes how components are placed within the screen boundaries or space allocated to Alexa on any device. You can define a layout one time and use it in multiple places within an APL document.
- link account card
- A special type of card (
LinkAccount) displayed in the Alexa App that tells the user to link their account. The user can start the account linking process right from this card. A custom skill can respond with this card if a user who has not linked their account tries to invoke an intent that requires authentication.
- low confidence errors
- When Alexa has low confidence in understanding what the customer said and proceeds either without requesting clarification or ends in the interaction.
- Conversational markers, or cues, are words or sentence clauses that indicate the status of a dialog to a customer. For example, “First,” “Next,” “I'll need some information from you,” etc.
- max error condition
- When consecutive dialogue errors occur, this terminates the interaction and is designed to keep Alexa from making the same mistake repeatedly.
- menu style prompt
- A prompt that asks the customer a question intended to elicit a response from a small set of possible options (recommended 5 or fewer). For example,
Helper for Minecraft. You can ask for a recipe, the ingredients of a potion, or game instructions. Now, which would you like?
- Describes an interface which has at least a voice and screen-based experience. Each input changes the way a customer can interact with the experience, but the two should work together fluidly.
- no intent invocation
- A customer's request with no intent or slot information. For example,
Alexa, open History Buff.
- When the customer takes an action that requires Alexa to inform them at a later time that an event is occurring or about to occur. The most common examples of this are alarms and timers. A notification can occur if nothing else is going on at all, or they also can occur in the form of an interruption while the customer is interacting with Alexa. In this case, the notification is delivered between turns during an interaction.
- open ended prompt
- A prompt that asks the customer a question intended to elicit a wide range of responses. For example,
What would you like to do?
- optional slot
- A slot that contains values that refine the user's request, but are not necessary for Alexa to complete the task. For example,
Alexa, ask History Buff what happened in history on June third.Here,
…June thirdis optional since History Buff can just give historical events for today if the user does not specify a date. As such, you should not ask the user for optional slot values if they exclude them.
- partial intent invocation
- A customer's request that contains the customer's intent, but is missing a required slot. For example,
Alexa, ask Horoscope for today's reading.Here, the required zodiac sign is missing, and Alexa needs to obtain that information from the customer.
- A string of text that should be spoken to the customer to ask for more information. You include the prompt text in your response to a customer's request. Types of prompts include: Open ended, Menu style, Re-prompt, and Implicit confirmation (Landmarking).
- A set of parameters that you can specify to change the default behavior or appearance of a component or response.
- A special kind of prompt used by Alexa when a response is not heard or clearly understandable, usually in the form of a question after a dialog error has occurred. The general purpose of a re-prompt is to help the customer recover from errors. For example,
Alexa, open Score Keeper.
Welcome back to Score Keeper. What's your update?
In this case, if the customer doesn't respond, Alexa would continue with helpful tips. For example,
You can add points for a player, ask for the current score, or start a new game. To hear a list of everything you can do, say Help. Now, what would you like to do?
- required slot
- A slot that contains values that are necessary for Alexa to complete the user's request. For example,
Alexa, ask Astrology Daily for the horoscope for Taurus.Without the name of the specific zodiac sign, Astrology Daily cannot provide a horoscope. If the user does not provide a value for a required slot, you must ask the user for that slot value.
- sample utterance
- A structured string of text that connects a specific intent to a likely utterance. You provide a set of sample utterances as part of your interaction model for a custom skill. When customers say one of these utterances, the Alexa service sends a request to your service that includes the corresponding intent.
- A set of actions or tasks that are accomplished by Alexa. Skills are like apps for Alexa, helping customers perform everyday tasks or engage with your content naturally with voice. Alexa provides built-in functionality, such as timers and alarms. You can use the Alexa Skills Kit to create skills for Alexa. A skill includes both the code, in the form of a cloud-based service, and the configuration provided on the developer console.
- An argument to an intent that gives Alexa more information about that request. For example,
Alexa, ask History Buff what happened on June third.In this statement,
…June thirdis the value of a date slot that refines the request. For a given intent, slots can be required or optional. To designate slots as required and let Alexa manage the conversation to collect the slot values, create a dialog model and then delegate the dialog to Alexa.
- Visual attributes and assets which control the look and feel of the Alexa experience. All components, layouts, and patterns inherit these values. Styles are delivered within themes and devices can expose multiple themes such as day and night mode.
- system error
- Occurs when something unexpected happened, unrelated to the dialogue between the customer and Alexa. For example, the call for a data service used to get the information the customer requested was unable to send Alexa that information.
- One of the words a user can say to tell Alexa to invoke a particular custom skill. This is used in combination with the invocation name for the skill. For example,
Alexa, tell Color Expert that my favorite color is red.There are several phrases users can say to start a conversation with Alexa. See Understanding How Users Invoke Custom Skills.
- A document that expresses the arrangement and display of visual components.
- text-to-speech (TTS)
- Converts a string of text to synthesized speech (Alexa's voice). The Alexa service can take plain text for TTS conversion.
- timeouts/silence/no response errors
- When the customer does not respond to a question Alexa asked. A re-prompt is usually played to encourage the customer to respond.
- touch interaction
- A touch on an Alexa-enabled device with a screen that produces a specified response, such as touching an item in a list on the screen to see more information about the item.
- A single request to or a response from Alexa. Sometimes
turnrefers to only the request side of a conversation, for example:
Alexa, open Horoscope.
What horoscope sign would you like?
Today's horoscope for Pisces is…
This example might be referred to as a two-turn interaction, rather than the 4 turns that it technically contained.
- The words a user says to Alexa to convey what they want to do, or to provide a response to a question Alexa asks. For skills that use one of the pre-built voice interaction models, Alexa provides predefined utterances and associated requests. For skills developed with the custom voice interaction model, you provide a set of sample utterances that map to a request (intent). For details, see About Voice Interaction Models.
- voice forward
- A voice-optimized multimodal concept where the GUI is optimized for voice. This means that buttons, links, and other touch affordances are replaced by voice-friendly affordances like action hints.
- voice user interface (VUI)
- A method for people to use voice input to interact with and control computers and devices. For a custom skill, the voice interface consists of a mapping between users' spoken utterances and the intents your cloud-based service can handle. See Interaction Model Schemas.
- wake word
- A command that the customer says to start speaking with Alexa. For example,
Alexa, open History Buff.Here,
Alexais the wake word. Alexa customers can select from a defined set of wake words:
- welcome message
- The message delivered when a customer invokes a skill without a request. For example,
Alexa, open Horoscope.Alexa would respond with a welcome message, such as:
Welcome back to Horoscope. Which sign would you like to hear a daily horoscope for?
A first time welcome message introduces the customer to the skill and provides a few commands the customer can use in that skill. A return welcome message greets the customer and prompts for a widely used task or required piece of information to continue the conversation.