Frequently Asked Questions
Find answers to the most common questions about the Algho platform.
General
What is Algho?
Algho is an artificial intelligence platform for creating and managing conversational virtual assistants, designed to improve customer experience and optimize support processes.
Which channels does Algho support?
Algho can be integrated on websites, mobile apps, WhatsApp, Facebook Messenger, Telegram and other messaging channels. Configuration varies depending on the chosen channel.
How do I get started with Algho?
To get started, log into the Algho platform and create your first assistant from the Assistant Settings section. The User Guide guides you step by step through the configuration.
Creating an assistant
What are the available methods to create an assistant?
There are 3 methods available: Wizard (quick creation with basic settings), Expert (full configuration of all settings) and Import file (from a .zip file of a previously exported assistant). See Creating an assistant.
What is configured in Wizard mode?
In the first step you enter the assistant's name, language, gender and voice. In the second step the icon, in the third step you customize some chat interface elements, in the fourth and fifth steps (only for accounts with Digital Human) you select the 3D model and background. See Creating an assistant#Wizard.
Which settings cannot be changed after Wizard creation?
All settings applied during creation can be modified later (see Assistant Settings), with the exception of the Assistant Language, which is defined during creation and cannot be changed afterwards. See Creating an assistant#Wizard.
What does Expert mode consist of?
Expert mode allows you to create an assistant by selecting all available settings at once in a single screen, without guided steps. See Creating an assistant#Expert.
How do I import an assistant from a file?
In Import file mode, simply select the .zip file containing the previously exported assistant and assign a name to the new assistant. See Creating an assistant#Import-file.
What is the purpose of the fourth and fifth Wizard steps?
The fourth step requires selecting the Digital Human and the fifth step the background. These steps are only required for Algho accounts that include the use of Digital Human. See Creating an assistant#Wizard.
Knowledge Base
What are intents and how do they work?
Intents are the fundamental units of the knowledge base. Each intent groups one or more user questions with their related answers. You can organize intents into categories, filter them by type (created or base) and set activation and expiration dates. For more details, see the Knowledge Base section.
How do I create a new intent?
From the Knowledge Base section, click the Create button at the bottom right and enter a required name and an optional category. You can also set the External ID field for third-party system integrations, and the Exclude if and Use if fields to control when the intent should be considered. See the intent creation guide.
What information is visible for each intent in the list?
Each intent shows: name, assigned category, number of questions, number of answers, number and type of linked suggestions, type of linked multimedia element, creation date and last modification date. Clicking the arrow displays a preview of the answer and its targeting settings. See Intents.
How do the "Exclude if" and "Use if" fields work?
Entering words in Exclude if excludes the intent if AT LEAST ONE of those words (or a synonym) is contained in the user's question. Use if includes the intent if AT LEAST ONE of the words (or a synonym) is contained in the user's question. See Intent creation.
How do I insert keywords in questions?
Keywords are words or groups of words that identify the question among others in the knowledge base. They are not mandatory, must be present in the question text and must be entered in their base form (masculine singular, infinitive). You do not need to insert synonyms for keywords. See Creating questions.
How do I link forms and suggestions to an answer?
When creating or editing an answer, you can link an existing form (same assistant language) and one or more suggestions. Suggestions can be automatic (chosen by the assistant among QAs with the appropriate option) or user-defined (selected manually from the list). See Forms and suggestions.
What are synonyms and how do I configure them?
Synonyms allow the assistant to recognize different words with the same meaning. They are configured in the Synonyms section of the knowledge base by creating groups of equivalent words (e.g. "send", "ship", "forward"). They can be imported and exported in Excel format. See the Synonyms section.
Can I merge multiple intents into one?
Yes, you can merge intents with the same answers in two ways: automatic merge (merges all questions with the same answers into a single intent) or manual merge (you select the intents to merge and the destination intent). The operation is not reversible. See Intent management.
What are courtesy replies and engagement messages?
Courtesy replies are shown when the assistant has no answer in the knowledge base. Engagement messages are sent after a period of user inactivity to reactivate the conversation. Both are customizable with targeting, multimedia elements and suggestions. See Courtesy replies and Engagement messages.
How does AI Gen for the knowledge base work?
AI Gen allows the assistant to use generative artificial intelligence to: select the best answer from the knowledge base, reformulate questions based on conversation context, reformulate answers based on question context, generate completely new answers for questions not in the knowledge base, and start forms or intents after a generated response. See AI Gen for the Knowledge Base.
How does answer generation work for questions not in the KB?
By enabling Enable answers to questions not present in the knowledge base, Algho generates completely new answers based solely on the provided prompt, without using information from the knowledge base or Smart Document Access. See AI Gen for the Knowledge Base#Answer-generation.
How does launching Forms and Intents work after an AI Gen generated answer?
Two mutually exclusive options: Launch form set by AI Gen links one or more forms with a prompt to set launch conditions; Launch intent after each generated answer sets an intent to launch after each generated answer. See AI Gen for the Knowledge Base#Launching-Forms-and-Intents.
How do I move questions between intents?
From the questions list of an intent, select one or more questions and click the Move button. On the next screen select the destination intent. If the moved question was the only one in the source intent, the latter is automatically deleted. See Intent management.
How do filters and sorting work in the knowledge base?
You can filter intents by type (Created/Base), by features (with form, with welcome suggestion, with suggestion disabled, with automatic suggestion, with custom suggestion, with expiration, with activation, multimedia) and by category. Sorting can be alphabetical, by insertion date or by modification date with adjustable items per page. See Knowledge Base#Filters.
What multimedia elements can be linked to an answer?
Each answer can link: image, video, link, file, QR Code and slideshow. Images and videos can be uploaded via URL or from the multimedia gallery. Links support automatic navigation if on the same domain as the assistant and the Open in frame option. See Multimedia elements.
How do I create a slideshow?
To create a slideshow, select the content type (image or video), enter accompanying text and the content via link, file or multimedia gallery. The slideshow introduction is defined by the answer text linked to the intent. See Multimedia elements#Slideshow.
How do intent activation and expiration work?
Each intent can be assigned an activation date and/or an expiration date that determine the period during which the intent is active. Before activation and after expiration, the intent is preserved but not active. See Activation, expiration, suggestion usage.
What are welcome suggestions and disambiguation suggestions?
Use as automatic suggestion allows the assistant to propose the intent as a suggestion. Use as welcome suggestion adds it to suggestions shown on first contact. The disambiguation and automatic suggestion text customizes the displayed text in these cases. See Activation, expiration, suggestion usage.
What command can be executed after a KB answer?
The command field sets a predefined action after the answer: Operator Request (with active Live Chat), Stop Conversation (Kiosk only) or Narration. See Command.
How do I import and export the knowledge base?
You can import intents from Excel (.xlsx) or JSON files, and export the knowledge base in the same formats. Excel import is limited to adding new intents (not modifying existing ones). See General options.
Assistant Settings
What comprehension parameters can I adjust?
In the assistant settings you can adjust three parameters: Confidence (accuracy vs. ambiguity risk), Flexibility (generalization vs. ambiguity risk) and Matching (syntactic vs. semantic matching). These parameters affect how the assistant interprets user requests. For more details, see Parameters.
How does assistant self-learning work?
The assistant can automatically learn from positive and negative user ratings. You can enable self-learning in the settings, choosing whether to learn from positive ratings, negative ratings (with suggestions) or from operators. Disambiguation self-learning is also available, which automatically adds a QA to the knowledge base after N choices. See Reinforcement.
Can I customize welcome messages and other replies?
Yes, from the General Assistant Settings section you can customize: welcome message (first interaction), welcome back message (returning users), disambiguation message, response waiting messages (with customizable waiting time), disengagement message (Kiosk only) and initial video (Kiosk only). See General settings.
What are response waiting messages?
Response waiting messages are shown when the assistant takes longer than the set Response waiting time. The displayed message is randomly chosen from those entered. See General Assistant Settings.
What are reply targeting conditions?
Targeting allows showing a reply only under certain conditions: by user emotion or attention (requires emotional recognition package), by source (interaction channel), by form (conditions based on completed fields) or by context (externally defined navigation conditions). See Targeting.
How does the Digital Human Editor work?
The Digital Human Editor allows you to configure the appearance, positioning, lighting and animations of the virtual avatar. It includes settings for: camera position and zoom (Avatar, Camera, FOV), preview grid, rotation presets, HDR tone mapping, lighting configuration, shadows (with ground plane), LUT for color correction (with .cube file and intensity), and animations for breathing, smile, speech, idle, lipsync (engine, weight, delay, lower/upper face strength, head gesture, audio sync) and additional animations. See Digital Human Editor.
How do I resize the avatar?
From the Digital Human section, click the green pencil icon at the bottom right. Select the mode (Desktop, Embed, Mobile, Kiosk, App), then adjust the Avatar (height) and Camera (zoom) parameters. The FOV controls the camera's field of view. See Resizing the Avatar.
How does the Multilingual option work?
The Multilingual option (available with AI Gen) allows the assistant to interpret questions in languages other than its set language. Users can select their preferred language and the assistant responds by automatically translating its answers. You can also enter a custom translation prompt. See Multilingual.
How do the "hide history" and "unanswered questions history" options work?
Hide conversation history from the user makes each conversation start from welcome (disables the welcome back). Unanswered questions history sets after how many days unanswered questions are automatically deleted (default 60 days). See Other settings.
How does the "enable assistant during update" option work?
If enabled, the assistant continues to answer even during a massive update (Excel/JSON) of the knowledge base. If disabled, it responds with "My information is being updated. Please try again later." See Other settings.
How does the conversation session duration work?
The conversation session duration option sets after how many minutes of inactivity the conversation is considered concluded (default: 15 minutes). Once it expires, if the user interacts again a new conversation is created and variables with "conversation" scope are reset. See Other settings.
How do I configure advertising banners in Kiosk mode?
In the Banner section of the settings (available only for accounts with the Kiosk feature) you can enable and set the display of advertising banners in the Kiosk interface, defining the dimensions in pixels and the transition time between banners. See Banners.
How do automatic commands after N interactions work?
In the Commands section you can enable automatic command activation after a certain number of messages, identical answers or courtesy replies. Available commands are: OPERATOR REQUEST, STOP CONVERSATION and NARRATION. See Commands.
How do I customize the chat interface?
From the Interface section you can customize the company logo, the assistant icon, chat colors (header text, background, interactive elements), the "powered by" text and response speed (slow, medium, fast, dynamic). See Interface.
How does response streaming work?
The enable response streaming option allows the assistant to deliver answers in streaming, reducing the waiting time perceived by the user. It is particularly effective with voice interaction, where the time needed to generate the voice reading is added to the time needed to generate the answer. See Interface.
What is the difference between Digital Human and background?
In the Digital Human section you can select a 3D model from the catalog and customize its display. In the Background section you can choose a background from the catalog or upload a custom one (image/video/URL). The background is displayed only through the Digital Human Interface. See Digital Human.
How does Call to action work?
The Call to action section allows enabling the option for users to start a Live Chat by clicking the appropriate icon, and to customize contact information clickable in the chat window. See Call to action.
Live Chat
How do I create operator groups?
Operator groups are created from the Operators section on the left. After naming the group, you can enable Priority management to set the notification order of operators, select the group operators, choose which assistants to manage and set a conversation filter via regular expression. See Live Chat#Operator-groups.
How does operator priority management work?
With priority management enabled, Live Chat is signaled first to the operator with the highest priority. After a customizable number of seconds (default 10s), if the operator does not respond, the chat is also signaled to subsequent operators. Without priority, all operators are in a single list. See Live Chat#Operator-groups.
How does the conversation filter in operator groups work?
The Conversation filter field allows filtering conversations based on the user's origin URL using a regular expression. For example, .*=ITA.* only manages conversations from URLs containing "=ITA". See Live Chat#Operator-groups.
How can an operator take over a conversation?
The operator can view active conversations (connected users, visible up to 15 minutes after the last message) and open conversations (taken over). By clicking the play icon, the operator can enter the conversation even if not expressly requested. Conversations can be locked with the padlock icon to prevent other operators from intervening. See Live Chat#Operator-Interface.
How does answer assistance work for the operator?
When a user asks a question, the system automatically searches the knowledge base. The Possible answers section shows the closest answers to the request; the operator can click an answer and send it directly. See Live Chat#Managing-a-conversation.
How does operator handover work during a Live Chat?
The operator can pass the conversation to a colleague by clicking the operator handover icon, selecting the colleague and sending an optional request message. The colleague receives a notification and can accept or decline. The operator who requested the handover receives a notification with the outcome. See Live Chat#Operator-handover.
How can an operator add questions to the knowledge base?
During a Live Chat, the operator can check a user's question and the related answer provided, and click + at the bottom right to add them to the assistant's knowledge base. See Live Chat#Managing-a-conversation.
How does automatic operator call work?
In the assistant settings you can enable automatic operator call after a certain consecutive number of courtesy replies. In this case, the Live Chat request notification takes a warning form, and the user is asked whether they want to accept or decline the transfer to an operator. If declined, the conversation is marked as "refused". See Assistant settings#Live-Chat.
Which Live Chat messages can be customized?
You can customize: operator connection message, operator disconnection message, operators unavailable message, operator connection request message and operator connection refusal message. See Assistant settings#Live-Chat.
Conversational Forms
How do I create a conversational form in Algho?
From the Forms section in the main menu, click Add. Then configure general settings (name, category, language, AI Gen prompt, welcome, failure and thank you messages), privacy consent options, AI Gen and auto-fill settings, knowledge base search, skip/interrupt texts, email/web service settings and the final command. See Conversational Forms#General-settings.
How does AI Gen work in forms?
AI Gen operates on two levels: 1st level — analyzes the user's initial question extracting information to automatically fill form fields; 2nd level — analyzes the user's answers to individual questions to validate them. Both levels can be active simultaneously. See Conversational Forms#AI-Gen-in-forms.
How do I enable AI Gen on forms?
Enter a preliminary prompt in the form's general settings. For 1st level, enable Form auto-filling and Use AI Gen for field auto-filling for each field. For 2nd level, enable Validate using AI Gen in the field's advanced functions. See How to enable AI Gen on forms.
What are nested forms and how do I configure them?
Nested forms allow you to create different question flows based on user answers. A "parent" form is created with admissible values, then separate ("nested") forms are created and linked to individual admissible values. At the end of each nested form, the flow always returns to the parent form. See Conversational Forms#Nested-forms.
How does knowledge base search work during a form?
By enabling Search among bot sources in case of field validation failure, if the user answers a form question with another question, the assistant searches the knowledge base, answers, and then re-asks the form question, making forms more flexible. See Knowledge base search.
How do I configure privacy consents in a form?
By enabling Privacy consent you choose which consents to activate (marketing, data sharing with third parties, newsletter, events and webinars). The user then selects them. See Consents and manual interruption.
How do I customize skip and interrupt texts in a form?
Skip question text customizes the option for non-mandatory fields, with catchable aliases. Interrupt completion text customizes the Cancel button. Form interruption message is shown to users who interrupt the form. See Skip and interrupt texts.
How do I configure email and web service settings for a form?
Send conversation by email allows receiving completed data via email. Attach files uploaded by users to the notification email attaches files up to 20 MB. Web Service URL and Async Web Service URL enable sending to external systems. Web service metadata passes a JSON to web services. See Email and web service settings.
Which commands can be executed after a form is completed?
Available commands are: OPERATOR REQUEST (starts Live Chat), START NEW CONVERSATION (reloads the assistant), RESTART NEW CONVERSATION (reloads keeping the same user ID) and STANDBY (interrupts the conversation, useful for VoIP). See Conversational Forms#Command.
What actions can be executed after a form?
EXECUTE SCRIPT allows running custom JavaScript (for browser automation). OPEN URL allows opening a URL via JSON. See Action.
How do I configure attempts and error messages for a field?
For each field you can set: success text (after a valid answer), error text (if the answer is not validated) and form interrupt attempts (from 0 to 99, default 3). After the maximum number of attempts, the form stops and the failure message is shown. See Conversational Forms#Messages-and-attempts.
How do I configure admissible values for a field?
After creating a field, from the summary screen click the Admissible values icon. Add values with a name (visible to the user) and optional aliases (synonyms to catch different terms). You can also configure display mode (HIDE, SCROLLABLE, FULL SCREEN) and matching options (semantic, with synonyms, ignore semantics). See Conversational Forms#Admissible-values.
What is the difference between semantic match and aliases in admissible values?
Semantic match catches pronunciation variations of the admissible value. Aliases catch synonyms: they require an exact match between what the user says or writes and the listed alias. See Difference between semantic match and alias.
What auto-fill options are available for fields?
Auto-fill field if already filled in the past avoids repeating questions already answered in other forms. Use AI Gen for field auto-filling extracts the information from the initial question using AI Gen. See Auto-fill options.
How does auto-filling after each field work?
The assistant extracts information from the answer to each field to fill subsequent ones. To enable it, you need: Automatic form filling, Use AI Gen to reformulate texts and Automatic filling after each field. See AI Gen and auto-fill options.
Statistics and Monitoring
What metrics are available in the Statistics section?
The Statistics section offers: number of conversations and messages, unanswered questions, disambiguations, average conversation depth, average/total duration, response speed, trend over time, response type (correct, courtesy, disambiguation), interaction type (form, engagement, questions), unique users per channel, completed/failed/incomplete/interrupted forms, input type, openings by domain and by type, Live Chat messages and actions. See Statistics.
How can I filter statistical data?
You can filter statistics by date range, by specific assistant and by status (e.g. active conversations). Conversation trend charts can be viewed by hour or by day, and response type can be filtered by hour, day or totals. See Statistics#Conversations.
What does "response speed" indicate in statistics?
Response speed is a metric that measures the time taken by the assistant to respond to user requests. It is calculated at the conversation level and represents the overall efficiency of the assistant in processing questions. See Statistics#Conversations.
Which in-depth sections are available for each assistant?
For each assistant the following sections are available: Conversations (performance in user interactions), Emotions (statistics on recognized emotions), Attention level (statistics on attention level) and Questions (ranking of most frequent requests). The Emotions and Attention sections are only available for enabled accounts. See Statistics#Assistants.
What do the Interaction type and Input type sections show?
Interaction type describes the different forms of interaction (form, engagement, questions). Input type catalogs the types of input received (keyboard, click, engagement, voice input). Unknown input refers to Facebook, Whatsapp and Telegram channels. See Statistics#Interaction-type and Statistics#Input-type.
What metrics are available for Live Chat in statistics?
The Live Chat Messages section contains statistics on messages exchanged in Live Chat mode (sent and received). The Live Chat Actions section reports actions taken during Live Chat sessions. See Live Chat Messages and Live Chat Actions.
What are Openings by domain and by type?
Openings by domain lists new conversation openings categorized by source domain (e.g. company website, app). Openings by type breaks down openings by type: text conversation, voice and text conversation, digital human conversation. See Statistics#Openings-by-domain and Statistics#Openings-by-type.
What data is available for Web Services calls?
The Web Services Calls section allows you to view statistical data related to web service calls made by the assistant, with the ability to set the time range and filter by assistant type and status. See Statistics#Web-Services-Calls.
How does the Conversation History work?
The Conversation History shows the complete list of conversations with filters for user ID, conversation ID and channel. Each conversation shows: date/time, messages, courtesy replies, answered questions, channel, Live Chat operator and user contact. Selecting Open Chat displays the full transcript. See Conversation History.
What do the response type codes in the History mean?
In the conversation transcript: WM = welcome message, QA = answer from knowledge base, QB = courtesy reply, QG = answer generated by AI Gen, SDA = answer from Smart Document Access, FORM = answer/question from a form. See Response type.
How does the Reinforcement section work?
Reinforcement displays: Unanswered questions (with the option to add them to the knowledge base), Disambiguations, Positively/Negatively rated answers (if rating is enabled), SDA (questions answered from documentation) and AI Gen (questions answered by AI Gen). All sections allow adding the question to the knowledge base. See Reinforcement.
How does the Consumables Dashboard work?
The Dashboard monitors account consumables: Textual (conversations with text interaction), Voice (conversations with voice interaction) and AI Gen (messages using AI Gen features). If multiple AI Gen features are used for one message, consumption equals the number of features used. See Consumables Dashboard.
Smart Document Access
How do I access Smart Document Access?
Smart Document Access is accessible by selecting Modules and then SDA 2.0 from the Algho main menu. See Smart Document Access.
How do I create folders and subfolders in SDA?
Select Add to create a folder. Inside it, create the subfolders, specifying name, document language and link validity duration. Options like Metadata and Enable image extraction can be enabled later. See Document management.
What document formats are supported by Smart Document Access?
Smart Document Access supports uploading documents in the following formats: PDF, DOC, DOCX and XLSX. Uploaded documents are indexed to be used by the assistant in responses. See Document management.
How does document indexing work?
After uploading, the file goes from Saved to Indexing in progress and finally to Indexing completed. The list supports filters by status, sorting and text search by file name or source URL. See Subfolder management.
How do I view the debug of an indexed document?
Selecting Open debug lets you view how the system indexed the document. Each colored box corresponds to a paragraph, i.e. a piece of the document representing grouped information. See Viewing a document.
What happens when I delete or replace an indexed document?
When you replace a document, the old file goes to Deleting status and is only deleted after the new one completes indexing. When you delete a document, it is no longer available for assistant responses. You can delete multiple documents at once via multi-select. See Document management.
How do I link an assistant to SDA documentation?
Go to Assistant Settings and then to the SDA section. You can link one or more subfolders at a time, provided they belong to the same folder. The assistant queries the documentation to generate responses. See Linking an assistant to documentation.
What search types are available in Smart Document Access?
There are 3 search modes available: Vectorial (converts questions into mathematical vectors and calculates similarity), Semantic (analyzes word meaning and linguistic relationships) and Hybrid (combines both, recommended). See Smart Document Access#Search-and-answer.
How does answer generation with AI Gen work in SDA?
By enabling Use AI Gen to generate responses, the response prompt editor is enabled, where you enter the instructions that the AI uses to generate the response based on the found paragraphs. You can also adjust the maximum number of input tokens and the length of the generated response. See Smart Document Access#Response-generation.
How do document display options work after a response?
The available options let you: not show the Show documents option, show only the most relevant documentation, or configure advanced settings to exclude documents from the crawler or manually uploaded ones. The Do not show the 'Show documents' option and Advanced preview settings options are mutually exclusive. See Smart Document Access#Documentation-options.
What additional options are available in SDA?
Hide the documentation used to generate the response if a link is present, Advanced settings for link display (by document source type) and Disable automatic navigation for links inserted in the response. See Additional options.
What are acronyms in Smart Document Access?
In the SDA search settings you can enter word associations (acronyms) to help the search. For example, entering "book" and "schedule" as acronyms of "reserve", the question "How can I schedule an appointment?" is searched as "How can I schedule or reserve an appointment?". See Smart Document Access#Search-settings.
How does launching Forms and Intents work in SDA?
Two mutually exclusive options: Launch form set by AI Gen links one or more forms with a prompt for launch conditions; Launch intent after each generated answer sets an intent to launch after each answer. See Launching Forms and Intents.
How does Proactive Search work in Smart Document Access?
Proactive Search allows the AI to assess whether the user's request is ambiguous and, if so, ask clarifying questions before providing an answer. It can be configured with three levels of granularity (Document, Paragraph, Body), a maximum number of questions, and custom prompts for the ambiguity and disambiguation instructions. See Proactive Search.
Smart Document Crawler
How does the Smart Document Access crawler work?
The crawler analyzes websites in two phases: navigation (maps the site structure by following links) and extraction (generates indexed PDFs from page content). Exclusions via regex, maximum depth and maximum pages can be configured, as well as weekly or monthly scan scheduling. See Smart Document Crawler.
How do I enable and configure the crawler?
Within an SDA subfolder, select Configure Smart Crawler, enable Enable on subfolder and add a configuration with a name. Then in Edit fields enter the starting URL and configure navigation options (exclusions, maximum depth, maximum pages), extraction rules (filters, selectors to remove via CSS/XPATH/Puppeteer) and scheduling (weekly or monthly). See Setting up the Crawler.
How do I view documents generated by the crawler?
The generated PDF documents are available in the configured SDA subfolder. Each document has the source URL as its File origin. See Viewing documents.
Other features
How does the Multimedia Gallery work?
The Multimedia Gallery allows uploading images, videos and documents for use in the knowledge base. It is accessible from Archive and then Multimedia Gallery. Each file shows name, type, preview and creation date. From the gallery you can copy the URL and edit the name. See Multimedia Gallery.
How does Text-to-Speech work?
The Text-to-Speech section allows entering pronunciation aliases to correct the assistant's reading errors. For each alias, enter the Searched word (as written) and the Word to use (as it should be pronounced). Useful for correcting accents or pronouncing acronyms (e.g. "CEO" → "Chief Executive Officer"). See Text-to-Speech.
How does Speech Recognition work?
The Speech Recognition section allows entering aliases to correct transcription errors in user voice input. For each alias, enter the Recognized word (as transcribed by the engine) and the Word to use (as it should be transcribed). Aliases apply to all assistants in the account. See Speech Recognition.
How do I create new Algho users?
In the Users section you can create access accounts for the Algho license, with the same permissions as the parent account. Enter name, surname, email, password and optional expiration. A notification email with login instructions is sent. See Users.
What are Global variables and how do they work?
Global variables let you create variables to be used for automatic form filling. When a user fills in a form field associated with a variable, the entered value is stored and automatically reused in the associated fields of subsequent forms. The scope can be "conversation" (variable reset at the end of the session) or "user" (persists across conversations). See Global variables.