{"id":31124,"date":"2026-07-01T12:35:40","date_gmt":"2026-07-01T10:35:40","guid":{"rendered":"https:\/\/botnation.ai\/train-chatbot-own-data\/"},"modified":"2026-07-28T16:36:06","modified_gmt":"2026-07-28T14:36:06","slug":"train-chatbot-own-data","status":"publish","type":"post","link":"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/","title":{"rendered":"Train a Chatbot on Your Own Data: Step-by-Step No-Code Guide"},"content":{"rendered":"<div class=\"bn-art\">\n<div class=\"bn-tldr\">\n<p><strong>\u201cTraining\u201d a chatbot on your own data does not mean retraining an AI model.<\/strong> In almost every case, it means <strong>feeding<\/strong> it: you hand it your web pages, your PDFs and your question-and-answer files, then an engine called RAG pulls the right passage out of your documents before the model writes the reply.<\/p>\n<p>The result: an assistant that answers with <strong>your<\/strong> information, updates in real time and hallucinates far less. With a no-code tool like Botnation, you get there in a few hours without writing a line of code. This guide shows you how, step by step.<\/p>\n<\/div>\n<p>A generic chatbot knows the whole world but nothing about your company: not your prices, not your shipping times, not your return policy. For it to actually answer your customers, you have to hand it <em>your<\/em> knowledge. The good news: the method has changed radically in the past two years. Nobody spends weeks drilling a model anymore; you connect it to your documents in a few clicks.<\/p>\n<p>This guide first clears up the confusion around the word \u201ctraining,\u201d then hands you the concrete playbook: which data to use, how to prepare it, and how to plug it into a no-code chatbot.<\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_85 counter-hierarchy ez-toc-counter ez-toc-custom ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Summary<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #3d351f;color:#3d351f\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #3d351f;color:#3d351f\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 eztoc-toggle-hide-by-default' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/#What_does_training_a_chatbot_on_your_own_data_actually_mean\" >What does training a chatbot on your own data actually mean?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/#RAG_fine-tuning_or_prompting_which_method_should_you_choose\" >RAG, fine-tuning or prompting: which method should you choose?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/#Which_data_can_you_use\" >Which data can you use?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/#Preparing_your_data_the_step_that_makes_the_difference\" >Preparing your data: the step that makes the difference<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/#Before_and_after_from_a_messy_page_to_a_useful_CSV\" >Before and after: from a messy page to a useful CSV<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/#Training_your_chatbot_on_your_data_step_by_step\" >Training your chatbot on your data, step by step<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/#Is_your_data_ready_to_feed_a_chatbot\" >Is your data ready to feed a chatbot?<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/#Best_practices_and_mistakes_to_avoid\" >Best practices and mistakes to avoid<\/a><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/#Do\" >Do<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/#Dont\" >Don\u2019t<\/a><\/li><\/ul><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/#Frequently_asked_questions\" >Frequently asked questions<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-12\" href=\"https:\/\/botnation.ai\/en\/train-chatbot-own-data\/#Bring_the_data_we_handle_the_rest\" >Bring the data, we handle the rest<\/a><\/li><\/ul><\/li><\/ul><\/nav><\/div>\n<h2 id=\"former-signifie-quoi\"><span class=\"ez-toc-section\" id=\"What_does_training_a_chatbot_on_your_own_data_actually_mean\"><\/span>What does training a chatbot on your own data actually mean?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The word \u201ctraining\u201d keeps a misunderstanding alive. Plenty of people picture taking an artificial intelligence model and teaching it all over again on their own text. That is true for a tiny minority of projects. For everything else, there are three very different ways to adapt a chatbot to your data.<\/p>\n<div class=\"bn-def\">\n<span class=\"bn-klabel\"><svg viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><circle cx=\"12\" cy=\"12\" r=\"9\"><\/circle><path d=\"M12 8h.01M11 12h1v4h1\"><\/path><\/svg>Definition<\/span>\n<p><strong>RAG (retrieval-augmented generation)<\/strong>: a technique that looks the answer up in a library of your documents, then passes it to a large language model (LLM) that rewrites it in natural language. Introduced in 2020 by Meta researchers led by Patrick Lewis, it lets you add or change a piece of information <strong>without retraining the model<\/strong>.<\/p>\n<\/div>\n<p>Here are the three levers, from lightest to heaviest:<\/p>\n<ul>\n<li><strong>The prompt (or \u201cinstructions\u201d):<\/strong> you give the chatbot a frame and a few fixed facts directly in its brief. Fast, but limited to short content.<\/li>\n<li><strong>RAG (feeding it data):<\/strong> you give it a library of documents; for each question, it finds the useful passages and answers from them. <strong>This is by far the most common setup<\/strong>, and what 9 people out of 10 mean when they say \u201ctrain my chatbot on my data.\u201d<\/li>\n<li><strong>Fine-tuning (retraining):<\/strong> you adjust the model\u2019s internal weights on thousands of examples. Useful to enforce a very specific style, but expensive, technical, and a poor fit for information that changes often.<\/li>\n<\/ul>\n<div class=\"bn-call bn-info\">\n<svg viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><circle cx=\"12\" cy=\"12\" r=\"9\"><\/circle><path d=\"M12 8h.01M11 12h1v4h1\"><\/path><\/svg>\n<div>\n<span class=\"bn-klabel\">The right instinct<\/span>\n<p>You want your chatbot to know your products, your procedures or your FAQ? Then you are looking for <strong>RAG<\/strong>, not fine-tuning. Keep the right verb in mind: you do not retrain it, you <strong>feed<\/strong> it.<\/p>\n<\/div>\n<\/div>\n<figure class=\"bn-fig\"><img decoding=\"async\" src=\"https:\/\/botnation.ai\/wp-content\/uploads\/2026\/07\/former-donnees-fig1.jpg\" alt=\"Data sources (web pages, PDFs, CSVs) brought together in a chatbot through RAG\"><figcaption>RAG brings your different data sources together so the chatbot can draw its answers from them.<\/figcaption><\/figure>\n<h2 id=\"rag-fine-tuning-prompt\"><span class=\"ez-toc-section\" id=\"RAG_fine-tuning_or_prompting_which_method_should_you_choose\"><\/span>RAG, fine-tuning or prompting: which method should you choose?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Each lever answers a different need. This table helps you choose based on what you actually want to hand your chatbot.<\/p>\n<div class=\"bn-tablewrap\">\n<table>\n<thead>\n<tr>\n<th>Method<\/th>\n<th>What it does<\/th>\n<th>Updates<\/th>\n<th>Technical level<\/th>\n<th>Best for<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Prompt \/ instructions<\/td>\n<td>Gives the model a frame and short fixed facts<\/td>\n<td>Immediate<\/td>\n<td>Very low (no-code)<\/td>\n<td>Tone, rules, a handful of stable facts<\/td>\n<\/tr>\n<tr>\n<td>RAG (feeding)<\/td>\n<td>The bot reads the answer in <strong>your<\/strong> documents before replying<\/td>\n<td>Instant with every document you add<\/td>\n<td>Low (no-code possible)<\/td>\n<td>Answering with your facts: FAQ, products, procedures, <strong>the everyday case<\/strong><\/td>\n<\/tr>\n<tr>\n<td>Fine-tuning<\/td>\n<td>Retrains the model on examples<\/td>\n<td>Slow and expensive (a new cycle)<\/td>\n<td>High (technical profiles)<\/td>\n<td>Enforcing a very specific style or format<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>Why does RAG dominate for business knowledge? Because it forces the model to lean on sources you control. As NVIDIA puts it, the approach bridges the gap between the model\u2019s frozen knowledge and your up-to-date information. Trying to inject facts through fine-tuning, on the other hand, usually blends your data with what the model learned originally, and multiplies the errors. The accepted rule today: <strong>RAG for facts, fine-tuning for style<\/strong>, and often a mix of the two for advanced cases.<\/p>\n<div class=\"bn-call bn-tip\">\n<svg viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><path d=\"M9 18h6M10 22h4M12 2a7 7 0 0 0-4 12c.5.5 1 1.5 1 3h6c0-1.5.5-2.5 1-3a7 7 0 0 0-4-12z\"><\/path><\/svg>\n<div>\n<span class=\"bn-klabel\">Worth remembering<\/span>\n<p>A Botnation chatbot runs on exactly that principle: a <strong>RAG engine paired with an LLM<\/strong>. You supply the data, it handles retrieving and rewording the right answer. No retraining to manage on your side.<\/p>\n<\/div>\n<\/div>\n<h2 id=\"quelles-donnees\"><span class=\"ez-toc-section\" id=\"Which_data_can_you_use\"><\/span>Which data can you use?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The raw material for a good chatbot is the knowledge you have already written down somewhere. Most companies own far more of it than they think. Here are the most useful sources, and the channel to feed each one in through.<\/p>\n<div class=\"bn-tablewrap\">\n<table>\n<thead>\n<tr>\n<th>Data source<\/th>\n<th>Examples<\/th>\n<th>How to feed it in<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Pages on your website<\/td>\n<td>Products, services, about, blog posts<\/td>\n<td>Web scraping (you pick the pages)<\/td>\n<\/tr>\n<tr>\n<td>FAQ and customer questions<\/td>\n<td>Frequently asked questions, recurring tickets<\/td>\n<td>Question-and-answer CSV file<\/td>\n<\/tr>\n<tr>\n<td>Reference documents<\/td>\n<td>Spec sheets, guides, terms and conditions, manuals<\/td>\n<td>File upload (PDF, Word, and so on)<\/td>\n<\/tr>\n<tr>\n<td>Structured data<\/td>\n<td>Catalog, prices, availability<\/td>\n<td>CSV file<\/td>\n<\/tr>\n<tr>\n<td>Customer service history<\/td>\n<td>Past conversations, template emails<\/td>\n<td>Reformat into question-and-answer pairs (CSV)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>With Botnation, these sources stack. <strong>Scraping<\/strong> crawls the web pages you choose, and you keep control over which ones get read or skipped. On top of that you can add <strong>files<\/strong> (PDF, CSV) to cover what never made it onto the site: internal documentation, procedures, special terms.<\/p>\n<p>Want to see what this looks like once it is live? Our roundup of <a href=\"https:\/\/botnation.ai\/en\/chatbot-example\/\">chatbot examples<\/a> shows the mechanism at work, and our guide to the <a href=\"https:\/\/botnation.ai\/en\/type-of-chatbot\/\">types of chatbots<\/a> helps you place yours.<\/p>\n<figure class=\"bn-fig\"><img decoding=\"async\" src=\"https:\/\/botnation.ai\/wp-content\/uploads\/2026\/07\/former-donnees-fig2.jpg\" alt=\"Structuring your data into question-and-answer pairs to feed a chatbot\"><figcaption>Rewriting your content as questions and answers: the most effective format for a chatbot.<\/figcaption><\/figure>\n<h2 id=\"preparer-donnees\"><span class=\"ez-toc-section\" id=\"Preparing_your_data_the_step_that_makes_the_difference\"><\/span>Preparing your data: the step that makes the difference<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>One principle sums it all up: <em>\u201cgarbage in, garbage out.\u201d<\/em> Messy data going in produces messy answers coming out. Your chatbot\u2019s quality depends first on how clean the material you hand it is. A few simple moves change everything.<\/p>\n<ol class=\"bn-steps\">\n<li><b>Clean and deduplicate<\/b>Delete outdated information, duplicates and answers that contradict each other. One version is the source of truth.<\/li>\n<li><b>Bring it up to date<\/b>Check prices, lead times, contact details. A chatbot quoting an old price does more harm than good.<\/li>\n<li><b>Structure it as questions and answers<\/b>The most effective format for a chatbot: a clear question, a short answer that stands on its own. That is what goes into a CSV.<\/li>\n<li><b>Split it into coherent chunks<\/b>One block, one idea. Avoid ten-page walls of text: RAG retrieves information far better from short, well-titled passages.<\/li>\n<\/ol>\n<div class=\"bn-call bn-tip\">\n<svg viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><path d=\"M9 18h6M10 22h4M12 2a7 7 0 0 0-4 12c.5.5 1 1.5 1 3h6c0-1.5.5-2.5 1-3a7 7 0 0 0-4-12z\"><\/path><\/svg>\n<div>\n<span class=\"bn-klabel\">Time-saving tip<\/span>\n<p>Sitting on a huge document or a raw ticket export? Hand it to <strong>your personal AI<\/strong> (ChatGPT, Claude, Gemini) and ask it to turn the thing into a <strong>question-and-answer<\/strong> table. You get a clean CSV back in minutes, ready to feed your chatbot. It is one of the highest-return shortcuts around.<\/p>\n<\/div>\n<\/div>\n<div class=\"bn-ex\">\n<div class=\"bn-ex-h\">\n<span class=\"bn-ex-n\">Ex<\/span>\n<div>\n<h3><span class=\"ez-toc-section\" id=\"Before_and_after_from_a_messy_page_to_a_useful_CSV\"><\/span>Before and after: from a messy page to a useful CSV<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span class=\"bn-ex-tag\">Real example<\/span><\/p><\/div>\n<\/div>\n<p>Take an online store whose \u201cShipping\u201d page crams everything into three dense paragraphs.<\/p>\n<div class=\"bn-ba\">\n<div class=\"biz\"><b>Before (raw)<\/b>\u201cOrders leave our warehouse within 24 to 48 business hours, standard delivery takes 3 to 5 days, express 24 hours, free over $60, returns accepted within 30 days\u2026\u201d<\/div>\n<div class=\"cli\"><b>After (Q\/A)<\/b>Q: \u201cHow long does delivery take?\u201d \u2192 A: \u201cOrders ship in 24 to 48 hours, then 3 to 5 days standard or 24 hours express.\u201d<br>Q: \u201cIs shipping free?\u201d \u2192 A: \u201cYes, on orders over $60.\u201d<\/div>\n<\/div>\n<\/div>\n<div class=\"bn-call bn-info\">\n<svg viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><circle cx=\"12\" cy=\"12\" r=\"9\"><\/circle><path d=\"M12 8h.01M11 12h1v4h1\"><\/path><\/svg>\n<div>\n<span class=\"bn-klabel\">Good to know<\/span>\n<p>A <strong>big question-and-answer CSV<\/strong> is often the single most powerful resource for a chatbot: every row is a ready-made answer with no ambiguity. Do not hesitate to supply hundreds of them. <strong>The more clean data your chatbot has, the more accurate it gets<\/strong>.<\/p>\n<\/div>\n<\/div>\n<h2 id=\"etapes-botnation\"><span class=\"ez-toc-section\" id=\"Training_your_chatbot_on_your_data_step_by_step\"><\/span>Training your chatbot on your data, step by step<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Once your data is gathered, hooking it up goes fast. Here is the typical path with a no-code platform like Botnation, no technical skills required.<\/p>\n<ol class=\"bn-steps\">\n<li><b>Create your chatbot<\/b>Start from a template or a blank page. You can also generate a chatbot by use case (lead capture, quiz, appointment booking) in a few minutes with the built-in AI.<\/li>\n<li><b>Connect your web pages<\/b>Enter your site address: scraping pulls in the content of the pages. You decide which ones are included or excluded.<\/li>\n<li><b>Add your files<\/b>Upload your PDFs and your question-and-answer CSVs to round out the knowledge base.<\/li>\n<li><b>Let RAG make the link<\/b>For each question, the engine finds the relevant passages in your data and the LLM writes a natural answer. Nothing to configure on the model side.<\/li>\n<li><b>Test and fix<\/b>Ask the questions real customers ask. Wrong answer, or no answer at all? Add the missing information to your knowledge base: the correction takes effect immediately.<\/li>\n<li><b>Deploy across your channels<\/b>Publish the chatbot on your website, and on WhatsApp, Messenger or Instagram too, all running on the same knowledge base.<\/li>\n<\/ol>\n<p>Looking for use cases? A chatbot fed with your data shines at <a href=\"https:\/\/botnation.ai\/en\/products\/client-support\/\">customer support<\/a>, <a href=\"https:\/\/botnation.ai\/en\/products\/lead-generation\/\">lead generation<\/a> and <a href=\"https:\/\/botnation.ai\/en\/products\/faq\/\">automated FAQ<\/a>, and it deploys across <a href=\"https:\/\/botnation.ai\/en\/channels\/\">all your channels<\/a>.<\/p>\n<div class=\"bn-check\">\n<span class=\"bn-klabel\"><svg viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><path d=\"M9 11l3 3L22 4\"><\/path><path d=\"M21 12v7a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V5a2 2 0 0 1 2-2h11\"><\/path><\/svg>Self-check<\/span>\n<h3><span class=\"ez-toc-section\" id=\"Is_your_data_ready_to_feed_a_chatbot\"><\/span>Is your data ready to feed a chatbot?<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>Check off what you already have. Your score and a recommendation appear live.<\/p>\n<ul>\n<li><label><input type=\"checkbox\">I have a website or up-to-date pages (products, services, about).<\/label><\/li>\n<li><label><input type=\"checkbox\">I have a FAQ or a list of the questions my customers ask most.<\/label><\/li>\n<li><label><input type=\"checkbox\">I have reference documents (PDFs, spec sheets, guides, terms and conditions).<\/label><\/li>\n<li><label><input type=\"checkbox\">I have a history of customer service conversations or emails.<\/label><\/li>\n<li><label><input type=\"checkbox\">My information is current and consistent (no contradictory answers).<\/label><\/li>\n<li><label><input type=\"checkbox\">I can structure part of it as questions and answers (CSV).<\/label><\/li>\n<\/ul>\n<div class=\"bn-result\">\n<b>Your readiness: <span class=\"bn-score\">0\/6<\/span><\/b>\n<div class=\"bnc-res\" data-v=\"prepare\">\n<p><strong>Groundwork needed.<\/strong> Gather your material first: list the questions customers ask most often and pull together your key pages and documents. Even a simple FAQ is enough to get started.<\/p>\n<\/div>\n<div class=\"bnc-res\" data-v=\"almost\">\n<p><strong>Almost there.<\/strong> You have a solid base. Structure it as questions and answers and close one or two gaps before plugging it into your chatbot.<\/p>\n<\/div>\n<div class=\"bnc-res\" data-v=\"ready\">\n<p><strong>Ready to feed your chatbot!<\/strong> Your data is rich and usable. All that is left is importing it into a no-code platform and testing it with real questions.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<h2 id=\"bonnes-pratiques\"><span class=\"ez-toc-section\" id=\"Best_practices_and_mistakes_to_avoid\"><\/span>Best practices and mistakes to avoid<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Feeding a chatbot is simple; keeping it reliable takes a little discipline. The points that make the difference:<\/p>\n<div class=\"bn-cols\">\n<div class=\"bn-col cli\">\n<h4><span class=\"ez-toc-section\" id=\"Do\"><\/span><svg viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><path d=\"M20 6L9 17l-5-5\"><\/path><\/svg>Do<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<ul>\n<li>Write answers that are <strong>short and self-contained<\/strong>, one idea per block.<\/li>\n<li><strong>Update<\/strong> regularly (prices, stock, procedures).<\/li>\n<li>Control <strong>which pages<\/strong> get scraped so the noise stays out.<\/li>\n<li>Test with <strong>real customer questions<\/strong>, not the ideal ones you wish they asked.<\/li>\n<\/ul>\n<\/div>\n<div class=\"bn-col biz\">\n<h4><span class=\"ez-toc-section\" id=\"Dont\"><\/span><svg viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><circle cx=\"12\" cy=\"12\" r=\"9\"><\/circle><path d=\"M12 8v5M12 16h.01\"><\/path><\/svg>Don\u2019t<span class=\"ez-toc-section-end\"><\/span><\/h4>\n<ul>\n<li>Feed in <strong>contradictory<\/strong> or expired documents.<\/li>\n<li>Dump unstructured <strong>walls of text<\/strong> and hope the AI will figure it out.<\/li>\n<li>Assume the chatbot will <strong>invent<\/strong> what you never gave it: no data, no reliable answer.<\/li>\n<li>Forget about <strong>confidentiality<\/strong>: only upload what the chatbot is allowed to say.<\/li>\n<\/ul>\n<\/div>\n<\/div>\n<div class=\"bn-call bn-warn\">\n<svg viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\"><path d=\"M12 3l9 16H3z\"><\/path><path d=\"M12 10v4M12 17h.01\"><\/path><\/svg>\n<div>\n<span class=\"bn-klabel\">Common mistake<\/span>\n<p>Mistaking <strong>quantity<\/strong> for <strong>quality<\/strong>. A hundred correct, up-to-date answers beat a thousand contradictory pages. Start with your 20 most frequent questions: they usually cover the bulk of the traffic.<\/p>\n<\/div>\n<\/div>\n<figure class=\"bn-fig\"><img decoding=\"async\" src=\"https:\/\/botnation.ai\/wp-content\/uploads\/2026\/07\/former-donnees-fig3.jpg\" alt=\"Testing a chatbot trained on your own data on a laptop\"><figcaption>Test the chatbot with real customer questions to spot the answers that still need filling in.<\/figcaption><\/figure>\n<h2 id=\"faq\"><span class=\"ez-toc-section\" id=\"Frequently_asked_questions\"><\/span>Frequently asked questions<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<details class=\"bn-faq\">\n<summary>How do I create my own chatbot?<\/summary>\n<div class=\"bn-faq-b\">\n<p>Pick a no-code platform (Botnation, for instance), create a chatbot from a template or by use case, then feed it your data: web pages, PDFs, question-and-answer files. You test, you fix, then you publish it on your website or your messaging apps. Not a line of code required.<\/p>\n<\/div>\n<\/details>\n<details class=\"bn-faq\">\n<summary>Can you train a chatbot on your own data?<\/summary>\n<div class=\"bn-faq-b\">\n<p>Yes, and it is the main use case. Watch the vocabulary though: in most projects you are not retraining the model, you are <strong>feeding<\/strong> it through RAG. You supply your documents, the chatbot draws its answers from them. Adding or updating a piece of information takes effect right away.<\/p>\n<\/div>\n<\/details>\n<details class=\"bn-faq\">\n<summary>Can I train ChatGPT on my own data?<\/summary>\n<div class=\"bn-faq-b\">\n<p>Not in the strict sense of modifying the ChatGPT model. You can, however, build an assistant that runs on your data, either through a custom GPT or through a dedicated platform that puts an LLM behind RAG. A solution like Botnation combines an LLM with your knowledge base: you end up with a \u201cChatGPT that knows your company,\u201d deployable across your channels.<\/p>\n<\/div>\n<\/details>\n<details class=\"bn-faq\">\n<summary>Do you need to code to train a chatbot on your data?<\/summary>\n<div class=\"bn-faq-b\">\n<p>No. No-code platforms handle the RAG, the scraping and the LLM for you. Your job stays on what really matters: gathering data that is clean, current and clearly worded.<\/p>\n<\/div>\n<\/details>\n<details class=\"bn-faq\">\n<summary>How much data do you need for a good chatbot?<\/summary>\n<div class=\"bn-faq-b\">\n<p>There is no magic threshold. Start with your frequently asked questions and your key pages, then enrich the base as real conversations come in. A large question-and-answer file speeds up the climb in quality noticeably, as long as it is clean and free of contradictions.<\/p>\n<\/div>\n<\/details>\n<details class=\"bn-faq\">\n<summary>What is the best tool to build a chatbot on your own data?<\/summary>\n<div class=\"bn-faq-b\">\n<p>The \u201cbest\u201d depends on your needs: target channels, budget, technical level. For a no-code chatbot that scrapes your website, ingests your files through RAG and then deploys to the web, WhatsApp, Messenger and Instagram, Botnation is easy to pick up and free to start with.<\/p>\n<\/div>\n<\/details>\n<div class=\"bn-cta\">\n<h3><span class=\"ez-toc-section\" id=\"Bring_the_data_we_handle_the_rest\"><\/span>Bring the data, we handle the rest<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>Build a chatbot that answers with YOUR information: scraping of your website, import of your PDFs and CSVs, built-in RAG and LLM engine. No coding, free to get started.<\/p>\n<p><a class=\"bn-cta-btn\" href=\"https:\/\/botnation.ai\/en\/\">Build my chatbot for free<\/a>\n<\/p><\/div>\n<\/div>\n<p><script>(function(){var s=document.createElement(\"style\");s.appendChild(document.createTextNode(\".bn-art{ --bn-cream:#faf8f2; --bn-card:#faf6ea; --bn-sand:#ebe3cb; --bn-sand-2:#f3ecd9; --bn-sand-zebra:#f6f0df; --bn-coral:#fe716b; --bn-coral-soft:#fdeeed; --bn-coral-line:#f6c9c6; --bn-blue:#5b7bfb; --bn-blue-soft:#eef1fe; --bn-blue-line:#c9d4fb; --bn-green:#7bbf66; --bn-green-soft:#eef6ea; --bn-ink:#3d351f; --bn-text:#414b56; --bn-muted:#6d6653; --bn-border:#e6dcc2; --bn-r:16px; --bn-r-sm:11px; --bn-sp:22px; --bn-sh:0 1px 2px rgba(61,53,31,.05),0 10px 26px rgba(61,53,31,.07); --bn-sh-sm:0 1px 2px rgba(61,53,31,.05),0 4px 12px rgba(61,53,31,.05); --bn-mono:'IBM Plex Mono','SFMono-Regular',ui-monospace,'Courier New',monospace; color:var(--bn-text); font-size:18px; line-height:1.75; max-width:820px; margin:0 auto; } .bn-art *{box-sizing:border-box} .bn-art p{margin:0 0 1.15em; color:var(--bn-text)} .bn-art h2{ color:var(--bn-ink); font-weight:700; line-height:1.25; font-size:1.72em; margin:2.2em 0 .7em; letter-spacing:-.01em; } .bn-art h3{color:var(--bn-ink); font-weight:700; font-size:1.22em; margin:1.8em 0 .5em} .bn-art a{color:var(--bn-blue); text-decoration:underline; text-underline-offset:2px; text-decoration-thickness:1px} .bn-art a:hover{color:var(--bn-coral)} .bn-art strong{color:var(--bn-ink); font-weight:700} .bn-art ul,.bn-art ol{margin:0 0 1.3em; padding-left:1.25em} .bn-art li{margin:.4em 0} .bn-art ul li::marker{color:var(--bn-coral)} .bn-art ol li::marker{color:var(--bn-blue); font-weight:700} .bn-klabel{ display:inline-flex; align-items:center; gap:7px; font-family:var(--bn-mono); font-size:12px; font-weight:600; text-transform:uppercase; letter-spacing:.12em; color:var(--bn-coral); margin:0 0 .2em; } .bn-klabel svg{width:15px;height:15px;flex:none} .bn-tldr{ background:var(--bn-card); border:1px solid var(--bn-border); border-left:4px solid var(--bn-coral); border-radius:var(--bn-r); padding:20px 24px; margin:0 0 30px; box-shadow:var(--bn-sh-sm); } .bn-tldr p{margin:0; color:var(--bn-text)} .bn-tldr p+p{margin-top:.6em} .bn-toc{ background:var(--bn-sand-2); border:1px solid var(--bn-sand); border-radius:var(--bn-r); padding:18px 22px; margin:0 0 34px; } .bn-toc .bn-klabel{color:var(--bn-coral)} .bn-toc ol{margin:.4em 0 0; padding-left:1.2em; columns:2; column-gap:28px} .bn-toc li{margin:.25em 0; break-inside:avoid} .bn-toc a{color:var(--bn-ink); text-decoration:none; font-weight:600; font-size:.96em} .bn-toc a:hover{color:var(--bn-coral); text-decoration:underline} .bn-stats{display:grid; grid-template-columns:repeat(3,1fr); gap:16px; margin:28px 0} .bn-stat{ background:var(--bn-card); border:1px solid var(--bn-border); border-radius:var(--bn-r); padding:20px 18px; text-align:center; box-shadow:var(--bn-sh-sm); } .bn-stat b{display:block; font-size:2em; line-height:1.1; color:var(--bn-coral); font-weight:800; letter-spacing:-.02em} .bn-stat span{display:block; margin-top:6px; font-size:.86em; color:var(--bn-muted); line-height:1.45} .bn-stat:nth-child(2) b{color:var(--bn-blue)} .bn-stat:nth-child(3) b{color:var(--bn-ink)} .bn-grid{display:grid; grid-template-columns:1fr 1fr; gap:18px; margin:26px 0} .bn-card{ background:var(--bn-card); border:1px solid var(--bn-border); border-radius:var(--bn-r); padding:22px; box-shadow:var(--bn-sh-sm); } .bn-card h4{margin:.1em 0 .35em; color:var(--bn-ink); font-size:1.06em; font-weight:700; display:flex; gap:9px; align-items:center} .bn-card h4 svg{width:20px;height:20px;flex:none;color:var(--bn-coral)} .bn-card p{margin:0; font-size:.96em} .bn-ex{ background:var(--bn-card); border:1px solid var(--bn-border); border-radius:var(--bn-r); padding:24px 26px; margin:20px 0; box-shadow:var(--bn-sh); position:relative; } .bn-ex-h{display:flex; align-items:center; gap:13px; margin-bottom:14px} .bn-ex-n{ flex:none; width:38px; height:38px; border-radius:11px; background:var(--bn-coral-soft); color:var(--bn-coral); display:flex; align-items:center; justify-content:center; font-weight:800; font-size:1.1em; font-family:var(--bn-mono); } .bn-ex-h h3{margin:0; font-size:1.18em} .bn-ex-tag{font-family:var(--bn-mono); font-size:11px; text-transform:uppercase; letter-spacing:.1em; color:var(--bn-muted); display:block; margin-top:2px} .bn-ex p{margin:.2em 0 .9em} .bn-ex .bn-ba{display:grid; grid-template-columns:1fr 1fr; gap:12px; margin-top:14px} .bn-ba div{border-radius:var(--bn-r-sm); padding:13px 15px; font-size:.9em; line-height:1.5} .bn-ba .biz{background:var(--bn-blue-soft); border:1px solid var(--bn-blue-line)} .bn-ba .cli{background:var(--bn-green-soft); border:1px solid #cfe6c4} .bn-ba b{display:block; font-family:var(--bn-mono); font-size:10.5px; text-transform:uppercase; letter-spacing:.08em; margin-bottom:4px; color:var(--bn-muted)} .bn-tablewrap{overflow-x:auto; margin:26px 0; border-radius:var(--bn-r); border:1px solid var(--bn-border); box-shadow:var(--bn-sh-sm)} .bn-art table{width:100%; border-collapse:collapse; background:var(--bn-card); font-size:.94em; min-width:520px} .bn-art thead th{background:var(--bn-ink); color:#fbf7ec; text-align:left; font-weight:700; padding:13px 16px; font-size:.92em} .bn-art tbody td{padding:12px 16px; border-top:1px solid var(--bn-border); color:var(--bn-text); vertical-align:top} .bn-art tbody tr:nth-child(even){background:var(--bn-sand-zebra)} .bn-art tbody td:first-child{font-weight:700; color:var(--bn-ink)} .bn-cols{display:grid; grid-template-columns:1fr 1fr; gap:18px; margin:26px 0} .bn-col{background:var(--bn-card); border:1px solid var(--bn-border); border-radius:var(--bn-r); padding:22px; box-shadow:var(--bn-sh-sm)} .bn-col h4{margin:0 0 12px; font-size:1.05em; color:var(--bn-ink); display:flex; align-items:center; gap:9px} .bn-col h4 svg{width:20px;height:20px;flex:none} .bn-col.biz h4 svg{color:var(--bn-blue)} .bn-col.cli h4 svg{color:var(--bn-green)} .bn-col ul{margin:0; padding:0; list-style:none} .bn-col li{position:relative; padding-left:26px; margin:.55em 0; font-size:.96em} .bn-col li::before{content:\\\"\\\"; position:absolute; left:0; top:.5em; width:13px; height:13px; border-radius:50%; background:var(--bn-coral-soft); border:2px solid var(--bn-coral)} .bn-col.biz li::before{background:var(--bn-blue-soft); border-color:var(--bn-blue)} .bn-col.cli li::before{background:var(--bn-green-soft); border-color:var(--bn-green)} .bn-call{ display:flex; gap:14px; border-radius:var(--bn-r); padding:18px 20px; margin:24px 0; background:var(--bn-card); border:1px solid var(--bn-border); box-shadow:var(--bn-sh-sm); } .bn-call svg{width:22px; height:22px; flex:none; margin-top:1px} .bn-call b{color:var(--bn-ink)} .bn-call p{margin:0; font-size:.95em} .bn-call .bn-klabel{margin-bottom:3px} .bn-tip{border-left:4px solid var(--bn-green)} .bn-tip svg{color:var(--bn-green)} .bn-tip .bn-klabel{color:var(--bn-green)} .bn-warn{border-left:4px solid var(--bn-coral)} .bn-warn svg{color:var(--bn-coral)} .bn-warn .bn-klabel{color:var(--bn-coral)} .bn-info{border-left:4px solid var(--bn-blue)} .bn-info svg{color:var(--bn-blue)} .bn-info .bn-klabel{color:var(--bn-blue)} .bn-def{background:var(--bn-blue-soft); border:1px solid var(--bn-blue-line); border-radius:var(--bn-r); padding:20px 24px; margin:24px 0} .bn-def .bn-klabel{color:var(--bn-blue)} .bn-def p{margin:0} .bn-steps{counter-reset:s; list-style:none; padding:0; margin:24px 0} .bn-steps li{position:relative; padding:0 0 4px 56px; margin:0 0 18px; min-height:40px} .bn-steps li::before{ counter-increment:s; content:counter(s); position:absolute; left:0; top:0; width:40px; height:40px; border-radius:12px; background:var(--bn-coral); color:#fff; font-weight:800; font-family:var(--bn-mono); display:flex; align-items:center; justify-content:center; box-shadow:var(--bn-sh-sm); } .bn-steps li b{display:block; color:var(--bn-ink); margin-bottom:2px} .bn-check{background:var(--bn-card); border:1px solid var(--bn-border); border-radius:var(--bn-r); padding:24px 26px; margin:28px 0; box-shadow:var(--bn-sh)} .bn-check h3{margin:.1em 0 .3em} .bn-check>p{font-size:.95em; color:var(--bn-muted); margin-bottom:14px} .bn-check ul{list-style:none; padding:0; margin:0 0 18px} .bn-check li{margin:0; border-top:1px solid var(--bn-border)} .bn-check li:first-child{border-top:none} .bn-check label{display:flex; align-items:flex-start; gap:13px; padding:12px 2px; cursor:pointer; font-size:.97em; color:var(--bn-text)} .bn-check input{appearance:none; -webkit-appearance:none; flex:none; width:22px; height:22px; margin-top:1px; border:2px solid var(--bn-coral-line); border-radius:7px; background:#fff; cursor:pointer; position:relative; transition:.15s} .bn-check input:checked{background:var(--bn-coral); border-color:var(--bn-coral)} .bn-check input:checked::after{content:\\\"\\\"; position:absolute; left:6px; top:2px; width:6px; height:11px; border:solid #fff; border-width:0 2.5px 2.5px 0; transform:rotate(45deg)} .bn-result{border-radius:var(--bn-r-sm); padding:16px 18px; background:var(--bn-coral-soft); border:1px solid var(--bn-coral-line); font-size:.96em} .bn-result b{color:var(--bn-ink)} .bn-result .bn-score{font-family:var(--bn-mono); font-weight:700; color:var(--bn-coral)} .bn-result .bnc-res{display:none; margin-top:10px} .bn-result .bnc-res.on{display:block} .bn-result .bnc-res p{margin:0; color:var(--bn-text)} .bn-faq{background:var(--bn-card); border:1px solid var(--bn-border); border-radius:var(--bn-r-sm); margin:0 0 12px; box-shadow:var(--bn-sh-sm); overflow:hidden} .bn-faq summary{cursor:pointer; padding:17px 20px; font-weight:700; color:var(--bn-ink); list-style:none; display:flex; justify-content:space-between; align-items:center; gap:14px; font-size:1.03em} .bn-faq summary::-webkit-details-marker{display:none} .bn-faq summary::after{content:\\\"+\\\"; font-family:var(--bn-mono); font-size:1.5em; color:var(--bn-coral); flex:none; line-height:1; transition:transform .2s} .bn-faq[open] summary::after{transform:rotate(45deg)} .bn-faq .bn-faq-b{padding:0 20px 18px; color:var(--bn-text)} .bn-faq .bn-faq-b p{margin:0} .bn-fig{margin:30px 0; text-align:center} .bn-fig img{width:100%; height:auto; border-radius:var(--bn-r); box-shadow:var(--bn-sh); display:block} .bn-fig figcaption{margin-top:10px; font-size:.85em; color:var(--bn-muted); font-style:italic} .bn-cta{background:var(--bn-ink); border-radius:var(--bn-r); padding:34px 32px; margin:36px 0 12px; text-align:center} .bn-cta h3{color:#fff; margin:0 0 .4em; font-size:1.4em} .bn-cta p{color:#e9e2cf; margin:0 auto 20px; max-width:560px; font-size:1em} .bn-cta-btn{display:inline-block; background:var(--bn-coral); color:#fff !important; text-decoration:none !important; font-weight:800; padding:15px 34px; border-radius:999px; font-size:1.02em; box-shadow:0 8px 22px rgba(254,113,107,.35); transition:.15s} .bn-cta-btn:hover{background:#ff8782; color:#fff !important} .bn-quiz{background:var(--bn-card); border:1px solid var(--bn-border); border-radius:var(--bn-r); padding:24px 26px; margin:28px 0; box-shadow:var(--bn-sh)} .bn-quiz .bnq-q{padding:14px 0; border-top:1px solid var(--bn-border)} .bn-quiz .bnq-q:first-of-type{border-top:none; padding-top:4px} .bn-quiz .bnq-qt{font-weight:700; color:var(--bn-ink); margin:0 0 10px; font-size:1.02em} .bn-quiz .bnq-opt{display:flex; align-items:flex-start; gap:12px; padding:9px 12px; margin:6px 0; cursor:pointer; font-size:.96em; color:var(--bn-text); border:1px solid var(--bn-border); border-radius:var(--bn-r-sm); background:#fff; transition:.15s} .bn-quiz .bnq-opt:hover{border-color:var(--bn-coral-line); background:var(--bn-coral-soft)} .bn-quiz .bnq-opt input{appearance:none; -webkit-appearance:none; flex:none; width:20px; height:20px; margin-top:1px; border:2px solid var(--bn-coral-line); border-radius:50%; background:#fff; cursor:pointer; position:relative; transition:.15s} .bn-quiz .bnq-opt input:checked{border-color:var(--bn-coral)} .bn-quiz .bnq-opt input:checked::after{content:\\\"\\\"; position:absolute; left:3px; top:3px; width:10px; height:10px; border-radius:50%; background:var(--bn-coral)} .bn-quiz .bnq-opt:has(input:checked){border-color:var(--bn-coral); background:var(--bn-coral-soft)} .bn-quiz .bnq-btn{margin-top:16px; display:inline-block; background:var(--bn-coral); color:#fff; border:none; font-weight:800; font-size:1em; padding:13px 30px; border-radius:999px; cursor:pointer; box-shadow:0 6px 16px rgba(254,113,107,.28); transition:.15s; font-family:inherit} .bn-quiz .bnq-btn:hover{background:#ff8782} .bn-quiz .bnq-res{display:none; margin-top:18px; padding:18px 20px; border-radius:var(--bn-r-sm); background:var(--bn-blue-soft); border:1px solid var(--bn-blue-line)} .bn-quiz .bnq-res.on{display:block} .bn-quiz #bnq-agent{background:var(--bn-coral-soft); border-color:var(--bn-coral-line)} .bn-quiz #bnq-hybrid{background:var(--bn-green-soft); border-color:#cfe6c4} .bn-quiz .bnq-rt{font-weight:800; color:var(--bn-ink); margin:0 0 6px; font-size:1.08em} .bn-quiz .bnq-res p{margin:0} .bn-spectrum{background:var(--bn-card); border:1px solid var(--bn-border); border-radius:var(--bn-r); padding:24px 26px; margin:28px 0; box-shadow:var(--bn-sh)} .bn-spectrum h3{margin:.1em 0 .3em} .bn-spectrum>p{font-size:.95em; color:var(--bn-muted); margin:0 0 20px} .bn-spec-track{margin:26px 4px 4px} .bn-spec-range{-webkit-appearance:none; appearance:none; width:100%; height:8px; border-radius:999px; background:var(--bn-sand); outline:none; cursor:pointer; margin:0} .bn-spec-range::-webkit-slider-thumb{-webkit-appearance:none; appearance:none; width:26px; height:26px; border-radius:50%; background:var(--bn-coral); border:3px solid #fff; box-shadow:var(--bn-sh-sm); cursor:pointer} .bn-spec-range::-moz-range-thumb{width:26px; height:26px; border-radius:50%; background:var(--bn-coral); border:3px solid #fff; box-shadow:var(--bn-sh-sm); cursor:pointer} .bn-spec-stops{display:flex; justify-content:space-between; margin-top:13px; font-family:var(--bn-mono); font-size:11px; text-transform:uppercase; letter-spacing:.07em; color:var(--bn-muted); gap:8px} .bn-spec-stops span{flex:1; cursor:pointer; transition:.15s; text-align:center} .bn-spec-stops span:first-child{text-align:left} .bn-spec-stops span:last-child{text-align:right} .bn-spec-stops span.on{color:var(--bn-coral); font-weight:700} .bns-pane{display:none; margin-top:22px; border-radius:var(--bn-r-sm); padding:20px 22px; background:var(--bn-sand-2); border:1px solid var(--bn-sand)} .bns-pane.on{display:block} .bns-pane h4{margin:0 0 3px; color:var(--bn-ink); font-size:1.14em} .bns-tag{font-family:var(--bn-mono); font-size:11px; text-transform:uppercase; letter-spacing:.1em; color:var(--bn-coral); display:block; margin-bottom:11px} .bns-pane>p{margin:0; font-size:.96em; color:var(--bn-text)} .bns-grid{display:grid; grid-template-columns:1fr 1fr; gap:12px; margin-top:15px} .bns-grid div{background:#fff; border:1px solid var(--bn-border); border-radius:var(--bn-r-sm); padding:11px 14px; font-size:.9em; color:var(--bn-text)} .bns-grid b{display:block; font-family:var(--bn-mono); font-size:10px; text-transform:uppercase; letter-spacing:.07em; color:var(--bn-muted); margin-bottom:3px} .bn-roi{background:var(--bn-card); border:1px solid var(--bn-border); border-radius:var(--bn-r); padding:24px 26px; margin:28px 0; box-shadow:var(--bn-sh)} .bn-roi h3{margin:.1em 0 .3em} .bn-roi>p{font-size:.95em; color:var(--bn-muted); margin:0 0 18px} .bn-roi-fields{display:grid; grid-template-columns:1fr 1fr; gap:20px 28px; margin:18px 0 24px} .bn-roi-field:last-child{grid-column:1\/-1} .bn-roi-field label{display:block; font-size:.9em; color:var(--bn-text); font-weight:600; margin-bottom:11px} .bn-roi-field output{font-family:var(--bn-mono); font-weight:700; color:var(--bn-coral)} .bn-roi-out{display:grid; grid-template-columns:repeat(3,1fr); gap:16px; margin-top:4px} .bn-roi-stat{background:var(--bn-sand-2); border:1px solid var(--bn-sand); border-radius:var(--bn-r); padding:20px 16px; text-align:center} .bn-roi-stat b{display:block; font-size:1.85em; line-height:1.05; color:var(--bn-coral); font-weight:800; letter-spacing:-.02em; font-family:var(--bn-mono)} .bn-roi-stat:nth-child(2) b{color:var(--bn-blue)} .bn-roi-stat:nth-child(3) b{color:var(--bn-ink)} .bn-roi-stat span{display:block; margin-top:7px; font-size:.82em; color:var(--bn-muted); line-height:1.4} .bn-roi-note{font-size:.84em; color:var(--bn-muted); margin:16px 0 0; font-style:italic} .bn-bot{background:var(--bn-card); border:1px solid var(--bn-border); border-radius:var(--bn-r); padding:22px 24px; margin:28px 0; box-shadow:var(--bn-sh)} .bn-bot h3{margin:.1em 0 .3em} .bn-bot>p{font-size:.95em; color:var(--bn-muted); margin:0 0 16px} .bn-bot-win{border:1px solid var(--bn-border); border-radius:var(--bn-r-sm); background:#fff; overflow:hidden} .bn-bot-bar{display:flex; align-items:center; gap:11px; padding:12px 16px; background:var(--bn-sand-2); border-bottom:1px solid var(--bn-border)} .bn-bot-ava{flex:none; width:32px; height:32px; border-radius:50%; background:var(--bn-coral-soft); display:flex; align-items:center; justify-content:center} .bn-bot-ava svg{width:19px; height:19px; color:var(--bn-coral)} .bn-bot-id b{display:block; color:var(--bn-ink); font-size:.95em; line-height:1.2} .bn-bot-id span{font-family:var(--bn-mono); font-size:10px; text-transform:uppercase; letter-spacing:.08em; color:var(--bn-green); display:inline-flex; align-items:center; gap:5px} .bn-bot-id span::before{content:\\\"\\\"; width:7px; height:7px; border-radius:50%; background:var(--bn-green)} .bn-bot-log{padding:16px; min-height:130px; max-height:320px; overflow-y:auto; display:flex; flex-direction:column; gap:10px} .bn-bot-msg{max-width:82%; padding:10px 14px; border-radius:15px; font-size:.95em; line-height:1.5} .bn-bot-msg.bot{align-self:flex-start; background:var(--bn-sand-2); color:var(--bn-text); border-bottom-left-radius:4px} .bn-bot-msg.user{align-self:flex-end; background:var(--bn-coral); color:#fff; border-bottom-right-radius:4px} .bn-bot-quick{display:flex; flex-wrap:wrap; gap:8px; padding:2px 16px 14px} .bn-bot-qbtn{font-family:inherit; font-size:.85em; color:var(--bn-ink); background:#fff; border:1px solid var(--bn-coral-line); border-radius:999px; padding:7px 14px; cursor:pointer; transition:.15s} .bn-bot-qbtn:hover{background:var(--bn-coral-soft); border-color:var(--bn-coral)} .bn-bot-form{display:flex; gap:8px; padding:12px 16px; border-top:1px solid var(--bn-border); background:var(--bn-sand-2)} .bn-bot-input{flex:1; min-width:0; font-family:inherit; font-size:.95em; color:var(--bn-ink); background:#fff; border:1px solid var(--bn-border); border-radius:999px; padding:10px 16px; outline:none} .bn-bot-input:focus{border-color:var(--bn-coral)} .bn-bot-send{flex:none; font-family:inherit; font-weight:700; font-size:.92em; color:#fff; background:var(--bn-coral); border:none; border-radius:999px; padding:10px 20px; cursor:pointer; transition:.15s} .bn-bot-send:hover{background:#ff8782} .bn-bot-note{font-size:.84em; color:var(--bn-muted); margin:14px 0 0; font-style:italic} @media(max-width:680px){ .bn-art{font-size:17px} .bn-stats,.bn-grid,.bn-cols,.bn-ex .bn-ba,.bns-grid,.bn-roi-fields,.bn-roi-out{grid-template-columns:1fr} .bn-roi-field:last-child{grid-column:auto} .bn-toc ol{columns:1} .bn-art h2{font-size:1.5em} .bn-bot-msg{max-width:90%} }\"));document.head.appendChild(s);})();(function(){var box=document.querySelector(\".bn-check\");if(!box){return;}var boxes=box.querySelectorAll(\"input[type=checkbox]\");var scoreEl=box.querySelector(\".bn-score\");var panes=box.querySelectorAll(\".bnc-res\");function upd(){var n=0,i;for(i=0;i<boxes.length;i++){if(boxes[i].checked){n++;}}if(scoreEl){scoreEl.textContent=n+\"\/\"+boxes.length;}var key=n>=5?\"ready\":(n>=3?\"almost\":\"prepare\");for(i=0;i<panes.length;i++){if(panes[i].getAttribute(\"data-v\")===key){panes[i].classList.add(\"on\");}else{panes[i].classList.remove(\"on\");}}}for(var j=0;j<boxes.length;j++){boxes[j].addEventListener(\"change\",upd);}upd();})();<\/script>\n<\/p>","protected":false},"excerpt":{"rendered":"<p>\u201cTraining\u201d a chatbot on your own data does not mean retraining an AI model. In almost every case, it means feeding it: you hand it your web pages, your PDFs and your question-and-answer files, then an engine called RAG pulls the right passage out of your documents before the model writes the reply. The result: [&hellip;]<\/p>\n","protected":false},"author":8,"featured_media":30594,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[362],"tags":[],"class_list":["post-31124","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-chatbot-en"],"acf":[],"_links":{"self":[{"href":"https:\/\/botnation.ai\/en\/wp-json\/wp\/v2\/posts\/31124","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/botnation.ai\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/botnation.ai\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/botnation.ai\/en\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/botnation.ai\/en\/wp-json\/wp\/v2\/comments?post=31124"}],"version-history":[{"count":2,"href":"https:\/\/botnation.ai\/en\/wp-json\/wp\/v2\/posts\/31124\/revisions"}],"predecessor-version":[{"id":31126,"href":"https:\/\/botnation.ai\/en\/wp-json\/wp\/v2\/posts\/31124\/revisions\/31126"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/botnation.ai\/en\/wp-json\/wp\/v2\/media\/30594"}],"wp:attachment":[{"href":"https:\/\/botnation.ai\/en\/wp-json\/wp\/v2\/media?parent=31124"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/botnation.ai\/en\/wp-json\/wp\/v2\/categories?post=31124"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/botnation.ai\/en\/wp-json\/wp\/v2\/tags?post=31124"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}