# Guides | onmsg > Plain-English guides to website chat software: what grounded AI means, how to build a conversation flow, how a shared inbox works, and what to check before you install. URL: https://onmsg.app/guide/ # Guides 28 guides on website chat: what the category is, how grounding works, how to build and branch a flow, how a shared inbox changes the way a small team answers, and what the reports actually measure. No sales pitch, just the answers. ## Start here Explainer ### How a Small Team Can Handle Website Enquiries Without Extra Headcount Deflect repetitive questions with grounded AI, capture context before handoff, and use a shared inbox for the conversations that need a person. Read guide [How a Small Team Can Handle Website Enquiries Without Extra Headcount →](/guide/handle-website-enquiries-without-extra-headcount/) Explainer ### How to Add Live Chat to Any Website with a Script Snippet Add website chat with a one-line script snippet. Where the snippet goes, generic steps for common site builders, the live/paused setting, and how to verify it loaded. Read guide [How to Add Live Chat to Any Website with a Script Snippet →](/guide/how-to-add-live-chat-to-any-website/) Decision guide ### Live Chat vs AI Chatbot vs Contact Form: Which Does Your Site Need? Compare live chat, AI chatbots and static contact forms for handling website enquiries, coverage, response speed and effort, and see how onmsg combines all three. Read guide [Live Chat vs AI Chatbot vs Contact Form: Which Does Your Site Need? →](/guide/live-chat-vs-ai-chatbot-vs-contact-form/) Explainer ### What Is Website Chat Software? A plain-English guide to website chat software: what a chat widget does, how live chat, AI answers and guided flows differ, and where it fits for a small business. Read guide [What Is Website Chat Software? →](/guide/what-is-website-chat-software/) ## Visual Bot Flow Builder See the feature [/features/visual-bot-flow-builder/ →](/features/visual-bot-flow-builder/) Explainer ### Branching by Page, Availability and Saved Answers Serve different flows by page (pricing vs homepage), route by availability (online vs offline), and branch by saved answer, practical examples of each. Read guide [Branching by Page, Availability and Saved Answers →](/guide/branching-by-page-availability-and-saved-answers/) Explainer ### How to Build a Greeting-to-Handoff Flow, Step by Step Walk through assembling a real onmsg flow: start with a greeting, branch by enquiry type, collect details with a form, add an AI Agent step, and route to a person. Read guide [How to Build a Greeting-to-Handoff Flow, Step by Step →](/guide/how-to-build-a-greeting-to-handoff-flow/) Decision guide ### How to Capture and Qualify Leads with Conversation Forms Use Form and One-field steps with required fields and validation to gather requirements before handoff, capture after-hours enquiries, and keep context for the team. Read guide [How to Capture and Qualify Leads with Conversation Forms →](/guide/capture-and-qualify-leads-with-conversation-forms/) Explainer ### The 11 Flow Step Types in onmsg, Explained Every onmsg flow step type explained: AI Agent, Question, Choices, One field, Form, Message, Image or video, Pause, By answer, By availability and By page. Read guide [The 11 Flow Step Types in onmsg, Explained →](/guide/the-11-flow-step-types-in-onmsg/) Decision guide ### Visual Flow Builder vs Scripted Chatbot: What's the Difference? Compare a visual, no-code flow builder with hand-coded and scripted bots, maintenance, speed, and who each suits, and see why non-technical teams prefer a canvas. Read guide [Visual Flow Builder vs Scripted Chatbot: What's the Difference? →](/guide/visual-flow-builder-vs-scripted-chatbot/) Explainer ### What Is a No-Code Chatbot Flow Builder? A no-code flow builder lets you design a chat conversation on a visual canvas, steps and branches, no coding. What it means, who it's for, and how it differs from hand-coding a bot. Read guide [What Is a No-Code Chatbot Flow Builder? →](/guide/what-is-a-no-code-chatbot-flow-builder/) ## Grounded AI Agent & Knowledge Base See the feature [/features/grounded-ai-agent/ →](/features/grounded-ai-agent/) Explainer ### How to Add Your Business Knowledge: Paste, Upload and URL Import Supply knowledge by pasting text, uploading PDF/DOCX/TXT/Markdown/CSV, or importing one public web page. See processing status, reindex and edit sources. Read guide [How to Add Your Business Knowledge: Paste, Upload and URL Import →](/guide/how-to-add-your-business-knowledge/) Explainer ### How to Reduce AI Chatbot Hallucinations with Grounding Controls Why chatbots invent facts, and how strict retrieval gating, refusal thresholds, handoff and source attribution help reduce it, controls that guide behaviour. Read guide [How to Reduce AI Chatbot Hallucinations with Grounding Controls →](/guide/how-to-reduce-ai-chatbot-hallucinations/) Decision guide ### Strict, Balanced and Open Grounding Modes Compared Compare onmsg's grounding modes: Strict (refuse when no relevant content), Balanced (prefer your knowledge), and Open (general conversation), plus when each fits. Read guide [Strict, Balanced and Open Grounding Modes Compared →](/guide/strict-balanced-and-open-grounding-modes-compared/) Decision guide ### Website Data Privacy: What Visitors' Chat Data Means for GDPR and CCPA What chat and enquiry data is collected, how retention settings differ by plan, and general GDPR/CCPA considerations for chat intake, guidance, not legal advice. Read guide [Website Data Privacy: What Visitors' Chat Data Means for GDPR and CCPA →](/guide/website-data-privacy-gdpr-and-ccpa/) Explainer ### What Does "Grounded AI" Mean for Website Chat? Grounded AI answers from your own content instead of general knowledge. What grounding is, why it matters, and how it differs from a general chatbot. Read guide [What Does "Grounded AI" Mean for Website Chat? →](/guide/what-does-grounded-ai-mean-for-website-chat/) Decision guide ### What Happens When the AI Can't Answer: Refusals and Human Handoff See what happens when onmsg's AI can't answer: a configurable refusal message, handoff after a set number of refusals, turn limits, timeouts, and provider errors. Read guide [What Happens When the AI Can't Answer: Refusals and Human Handoff →](/guide/what-happens-when-the-ai-cant-answer/) ## Website Chat & Widget Customization See the feature [/features/website-chat-widget/ →](/features/website-chat-widget/) Explainer ### How to Customize Your Chat Widget's Colours, Fonts and Placement Control your widget's placement and offsets, colours for widget, header, messages and inputs, fonts and sizes, launcher icons and teaser images, and framing. Read guide [How to Customize Your Chat Widget's Colours, Fonts and Placement →](/guide/how-to-customize-your-chat-widget/) Explainer ### Setting Business Hours, Timezone and After-Hours Behaviour Set business hours and timezone, choose configurable after-hours behaviour, enable offline message intake, and pair it with By-availability flow branching. Read guide [Setting Business Hours, Timezone and After-Hours Behaviour →](/guide/setting-business-hours-and-after-hours-behaviour/) Explainer ### Using Custom CSS to Match the Widget to Your Brand Use custom CSS for the widget, teaser and messages when the visual controls aren't enough. When to use CSS versus the built-in controls, and keeping it responsive. Read guide [Using Custom CSS to Match the Widget to Your Brand →](/guide/using-custom-css-to-match-your-brand/) ## Shared Team Inbox See the feature [/features/shared-team-inbox/ →](/features/shared-team-inbox/) Explainer ### How the Shared Inbox Routes and Assigns Conversations See how teams coordinate: assign a conversation to a teammate or return it to the queue, resolve and reopen, and search by contact, messages, notes and tags. Read guide [How the Shared Inbox Routes and Assigns Conversations →](/guide/how-the-shared-inbox-routes-and-assigns-conversations/) Explainer ### Saved Replies and Private Notes for Faster Team Responses Use personal and shared saved replies with shortcuts (insert then send, not auto-send) and append-only private notes with author and timestamp. Read guide [Saved Replies and Private Notes for Faster Team Responses →](/guide/saved-replies-and-private-notes/) Decision guide ### Shared Team Inbox vs a Shared Email Address for Support Why a shared inbox beats a group email for support: ownership and assignment vs reply-all confusion, drafts and notes, searchable history, and chat handoff. Read guide [Shared Team Inbox vs a Shared Email Address for Support →](/guide/shared-team-inbox-vs-a-shared-email-address/) ## Multi-Site & API See the feature [/features/multi-site-api/ →](/features/multi-site-api/) Explainer ### Managing Multiple Websites and Brands from One Workspace Run chat across several websites and brands from one workspace, with separate configuration, conversations, knowledge, flows and team per site. Read guide [Managing Multiple Websites and Brands from One Workspace →](/guide/managing-multiple-websites-and-brands/) Explainer ### What the onmsg Site API Can Do: Ask, Read, Hand Off, Manage Knowledge A clear map of the onmsg site API: ask the AI a question, read a conversation, hand a conversation into the human inbox, and manage knowledge sources. Read guide [What the onmsg Site API Can Do: Ask, Read, Hand Off, Manage Knowledge →](/guide/what-the-onmsg-site-api-can-do/) Decision guide ### When to Use the Embeddable Widget vs the API Choose between the drop-in widget for fast standard installs and the API for custom UIs and integrations, and when to combine both. Read guide [When to Use the Embeddable Widget vs the API →](/guide/when-to-use-the-widget-vs-the-api/) ## Response-Time Reporting See the feature [/features/response-time-reporting/ →](/features/response-time-reporting/) Explainer ### Reading First-Response, Coverage and Resolution Timing How to read onmsg's report rows: first-response times, coverage and unanswered conversations, average/median/90th-percentile timing, and resolution figures. Read guide [Reading First-Response, Coverage and Resolution Timing →](/guide/reading-first-response-coverage-and-resolution-timing/) Explainer ### What the Response-Time Reports Measure (and What They Don't) Understand onmsg's response-time reporting scope: retained history and elapsed UTC time, with bot messages and notes excluded from first human response. Read guide [What the Response-Time Reports Measure (and What They Don't) →](/guide/what-the-response-time-reports-measure/) ## AI Provider Choice (BYOK) See the feature [/features/ai-provider-choice/ →](/features/ai-provider-choice/) Decision guide ### Included AI vs Bring-Your-Own Provider Key: Which to Choose Decide between onmsg's included AI allowance and connecting your own provider key: what the allowance covers, when BYOK makes sense, and what BYOK doesn't change. Read guide [Included AI vs Bring-Your-Own Provider Key: Which to Choose →](/guide/included-ai-vs-bring-your-own-provider-key/) ![](/images/hero/abstract-3d-illustration-of-a-website-chat-widget-.webp) No credit card required ## Reading is fine. Trying it is better Create a site, add three knowledge sources, and watch how the answers change. The free plan is enough to see it working. Start free [https://chat.onmsg.app →](https://chat.onmsg.app) Compare plans [/pricing/ →](/pricing/) - Free plan available - Installs with a script snippet - Your content, your controls