{"id":254017,"date":"2026-02-16T02:52:30","date_gmt":"2026-02-16T02:52:30","guid":{"rendered":"https:\/\/wordpress.org\/plugins\/smartbot-assistant-ai-powered-content-helper\/"},"modified":"2026-07-10T12:08:45","modified_gmt":"2026-07-10T12:08:45","slug":"sentient-ai","status":"publish","type":"plugin","link":"https:\/\/fi.wordpress.org\/plugins\/sentient-ai\/","author":8205952,"comment_status":"closed","ping_status":"closed","template":"","meta":{"version":"2.10.1","stable_tag":"2.10.1","tested":"6.9.4","requires":"5.8","requires_php":"7.4","requires_plugins":null,"header_name":"Sentient AI","header_author":"Maidul","header_description":"AI-powered chatbot plugin for WordPress with FAQ management and multiple AI provider support.","assets_banners_color":"6e8ccb","last_updated":"2026-07-10 12:08:45","external_support_url":"","external_repository_url":"","donate_link":"","header_plugin_uri":"","header_author_uri":"","rating":0,"author_block_rating":0,"active_installs":0,"downloads":502,"num_ratings":0,"support_threads":0,"support_threads_resolved":0,"author_block_count":0,"sections":["description","installation","faq","changelog"],"tags":{"1.1.1":{"tag":"1.1.1","author":"maidulcu","date":"2026-07-09 04:42:38"},"1.2.0":{"tag":"1.2.0","author":"maidulcu","date":"2026-07-09 05:09:00"},"1.3.0":{"tag":"1.3.0","author":"maidulcu","date":"2026-07-09 05:58:28"},"1.4.0":{"tag":"1.4.0","author":"maidulcu","date":"2026-07-09 06:15:42"},"1.4.1":{"tag":"1.4.1","author":"maidulcu","date":"2026-07-09 06:44:46"},"2.0.0":{"tag":"2.0.0","author":"maidulcu","date":"2026-07-09 07:05:54"},"2.1.0":{"tag":"2.1.0","author":"maidulcu","date":"2026-07-09 07:39:04"},"2.10.0":{"tag":"2.10.0","author":"maidulcu","date":"2026-07-10 12:01:38"},"2.10.1":{"tag":"2.10.1","author":"maidulcu","date":"2026-07-10 12:08:45"},"2.2.0":{"tag":"2.2.0","author":"maidulcu","date":"2026-07-09 07:51:23"},"2.3.0":{"tag":"2.3.0","author":"maidulcu","date":"2026-07-09 08:04:48"},"2.4.0":{"tag":"2.4.0","author":"maidulcu","date":"2026-07-09 08:14:55"},"2.5.0":{"tag":"2.5.0","author":"maidulcu","date":"2026-07-09 08:22:12"},"2.6.0":{"tag":"2.6.0","author":"maidulcu","date":"2026-07-09 12:51:41"},"2.8.0":{"tag":"2.8.0","author":"maidulcu","date":"2026-07-10 11:28:32"},"2.9.0":{"tag":"2.9.0","author":"maidulcu","date":"2026-07-10 11:50:39"}},"upgrade_notice":{"2.10.1":"<p>WooCommerce deep integration with HPOS support, product vectorization for semantic search, and real-time webhooks for orders\/stock\/reviews. Combined with all 2.8.0 features (Vector Database, MCP Server, GEO Scanner).<\/p>","2.8.0":"<p>Semantic vector search with two-tier architecture. Local MySQL engine works on all shared hosting. Pinecone and Supabase cloud engines for scale. Combined with all 2.7.0 features (MCP Server, GEO Scanner, browser FAQ matcher) and multiple bug fixes.<\/p>","2.7.0":"<p>MCP Server for AI agent integration, GEO Scanner for AI search optimization, browser-based FAQ matcher, plus multiple stability fixes and the new Help documentation tab.<\/p>","2.6.0":"<p>Security hardening, redesigned UI, and critical bug fixes. Recommended update for all installations.<\/p>","2.2.0":"<p>Local Brain \u2014 privacy-first local AI processing with zero API costs and offline support.<\/p>","2.1.0":"<p>WordPress Autopilot \u2014 AI agent that manages your site through chat commands.<\/p>","2.0.0":"<p>Sentient Memory \u2014 AI learns from every interaction and improves response quality over time.<\/p>","1.4.0":"<p>Empathy Engine \u2014 AI detects user emotion and adapts its response tone accordingly.<\/p>","1.3.0":"<p>Glass Box \u2014 Confidence scores and source attribution on every AI response.<\/p>","1.2.0":"<p>Multi-turn conversations with persistent chat history and configurable context.<\/p>"},"ratings":[],"assets_icons":[],"assets_banners":{"banner-772x250.png":{"filename":"banner-772x250.png","revision":3601500,"resolution":"772x250","location":"assets","locale":"","width":772,"height":431}},"assets_blueprints":{},"all_blocks":[],"tagged_versions":["1.1.1","1.2.0","1.3.0","1.4.0","1.4.1","2.0.0","2.1.0","2.10.0","2.10.1","2.2.0","2.3.0","2.4.0","2.5.0","2.6.0","2.8.0","2.9.0"],"block_files":[],"assets_screenshots":{"screenshot-1.png":{"filename":"screenshot-1.png","revision":3601500,"resolution":"1","location":"assets","locale":"","width":1131,"height":1433},"screenshot-10.png":{"filename":"screenshot-10.png","revision":3601500,"resolution":"10","location":"assets","locale":"","width":1220,"height":1384},"screenshot-2.png":{"filename":"screenshot-2.png","revision":3601500,"resolution":"2","location":"assets","locale":"","width":1222,"height":626},"screenshot-3.png":{"filename":"screenshot-3.png","revision":3601500,"resolution":"3","location":"assets","locale":"","width":1225,"height":724},"screenshot-4.png":{"filename":"screenshot-4.png","revision":3601500,"resolution":"4","location":"assets","locale":"","width":1222,"height":696},"screenshot-5.png":{"filename":"screenshot-5.png","revision":3601500,"resolution":"5","location":"assets","locale":"","width":1227,"height":909},"screenshot-6.png":{"filename":"screenshot-6.png","revision":3601500,"resolution":"6","location":"assets","locale":"","width":1221,"height":839},"screenshot-7.png":{"filename":"screenshot-7.png","revision":3601500,"resolution":"7","location":"assets","locale":"","width":1221,"height":1369},"screenshot-8.png":{"filename":"screenshot-8.png","revision":3601500,"resolution":"8","location":"assets","locale":"","width":1224,"height":795},"screenshot-9.png":{"filename":"screenshot-9.png","revision":3601500,"resolution":"9","location":"assets","locale":"","width":1221,"height":866}},"screenshots":{"1":"Settings page \u2014 Provider configuration, API keys, widget settings, and feature toggles","2":"Query Logs \u2014 Searchable conversation history with response types and FAQ linking","3":"Conversations \u2014 Session-based conversation viewer with message threading","4":"Low Confidence Queries \u2014 AI answers below threshold with create-FAQ actions","5":"Sentiment Analytics \u2014 Emotion distribution (happy, frustrated, confused) with time range filters","6":"Learning Dashboard \u2014 Topic clustering, trending topics, auto-FAQ suggestions, and low quality tracking","7":"WordPress Autopilot \u2014 Available commands, activity log, and site management stats","8":"Sentient Insights \u2014 Priority-ranked recommendations with action suggestions","9":"Train Assistant \u2014 Content type selection, field configuration, and training data preview","10":"Import FAQs \u2014 CSV upload with format instructions and tips"}},"plugin_section":[262246],"plugin_tags":[191735,2364,2369,1643,194533],"plugin_category":[47],"plugin_contributors":[80683],"plugin_business_model":[],"class_list":["post-254017","plugin","type-plugin","status-publish","hentry","plugin_section-dashboard-widgets","plugin_tags-ai-chatbot","plugin_tags-chatbot","plugin_tags-customer-support","plugin_tags-faq","plugin_tags-openai","plugin_category-education-and-support","plugin_contributors-maidulcu","plugin_committers-maidulcu"],"banners":{"banner":"https:\/\/ps.w.org\/sentient-ai\/assets\/banner-772x250.png?rev=3601500","banner_2x":false,"banner_rtl":false,"banner_2x_rtl":false},"icons":{"svg":false,"icon":"https:\/\/s.w.org\/plugins\/geopattern-icon\/sentient-ai_6e8ccb.svg","icon_2x":false,"generated":true},"screenshots":[{"src":"https:\/\/ps.w.org\/sentient-ai\/assets\/screenshot-1.png?rev=3601500","caption":"Settings page \u2014 Provider configuration, API keys, widget settings, and feature toggles"},{"src":"https:\/\/ps.w.org\/sentient-ai\/assets\/screenshot-2.png?rev=3601500","caption":"Query Logs \u2014 Searchable conversation history with response types and FAQ linking"},{"src":"https:\/\/ps.w.org\/sentient-ai\/assets\/screenshot-3.png?rev=3601500","caption":"Conversations \u2014 Session-based conversation viewer with message threading"},{"src":"https:\/\/ps.w.org\/sentient-ai\/assets\/screenshot-4.png?rev=3601500","caption":"Low Confidence Queries \u2014 AI answers below threshold with create-FAQ actions"},{"src":"https:\/\/ps.w.org\/sentient-ai\/assets\/screenshot-5.png?rev=3601500","caption":"Sentiment Analytics \u2014 Emotion distribution (happy, frustrated, confused) with time range filters"},{"src":"https:\/\/ps.w.org\/sentient-ai\/assets\/screenshot-6.png?rev=3601500","caption":"Learning Dashboard \u2014 Topic clustering, trending topics, auto-FAQ suggestions, and low quality tracking"},{"src":"https:\/\/ps.w.org\/sentient-ai\/assets\/screenshot-7.png?rev=3601500","caption":"WordPress Autopilot \u2014 Available commands, activity log, and site management stats"},{"src":"https:\/\/ps.w.org\/sentient-ai\/assets\/screenshot-8.png?rev=3601500","caption":"Sentient Insights \u2014 Priority-ranked recommendations with action suggestions"},{"src":"https:\/\/ps.w.org\/sentient-ai\/assets\/screenshot-9.png?rev=3601500","caption":"Train Assistant \u2014 Content type selection, field configuration, and training data preview"},{"src":"https:\/\/ps.w.org\/sentient-ai\/assets\/screenshot-10.png?rev=3601500","caption":"Import FAQs \u2014 CSV upload with format instructions and tips"}],"raw_content":"<!--section=description-->\n<p>Sentient AI is a comprehensive WordPress chatbot platform that combines AI-powered conversations with site management, semantic search, and external AI agent integration. It supports multiple AI providers, runs locally without API keys for FAQ matching, and offers enterprise-grade features for privacy-conscious organizations.<\/p>\n\n<h4>Core Capabilities<\/h4>\n\n<ul>\n<li><p><strong>Multi-Provider AI<\/strong> \u2014 Supports OpenAI (GPT-4o, GPT-4, GPT-3.5), Claude (Anthropic), Google Gemini, OpenRouter, and Hugging Face. Switch providers without changing your workflow.<\/p><\/li>\n<li><p><strong>Semantic Vector Search<\/strong> \u2014 Two-tier architecture: Local MySQL engine for shared hosting (no custom PHP extensions needed) and cloud engines (Pinecone, Supabase) for scale. Finds content by meaning, not just keywords.<\/p><\/li>\n<li><p><strong>Browser-Based FAQ Matching<\/strong> \u2014 Answers common questions instantly in the visitor's browser. Zero API costs, works offline, no data leaves the site. Falls back to cloud AI when needed.<\/p><\/li>\n<li><p><strong>WordPress Autopilot<\/strong> \u2014 AI agent that manages your WordPress site through chat commands: create posts, check for updates, scan for broken images, clear cache, and more. Administrator-only access.<\/p><\/li>\n<li><p><strong>MCP Server<\/strong> \u2014 Expose your chatbot, FAQs, and site analytics to external AI agents via the Model Context Protocol. Connect Claude Desktop, Cursor, or custom AI agents directly to your WordPress installation.<\/p><\/li>\n<li><p><strong>GEO Scanner<\/strong> \u2014 Analyze content for Generative Engine Optimization. Score each post\/page across 10 factors that determine how AI search engines (Google SGE, Perplexity, ChatGPT Search) evaluate your content. One-click fixes for schema markup.<\/p><\/li>\n<li><p><strong>Empathy Engine<\/strong> \u2014 Real-time emotion detection adapts the AI's response tone. Automatically escalates frustrated users to human support.<\/p><\/li>\n<li><p><strong>Glass Box Transparency<\/strong> \u2014 Every AI response shows a confidence score (0-100%) with source attribution. Admins can review low-confidence queries and improve their FAQ database.<\/p><\/li>\n<\/ul>\n\n<h4>Designed for Every Hosting Environment<\/h4>\n\n<ul>\n<li><strong>Shared hosting (Bluehost, SiteGround, GoDaddy, HostGator)<\/strong> \u2014 Local MySQL vector engine works without SSH access or custom PHP extensions<\/li>\n<li><strong>Cloud \/ VPS<\/strong> \u2014 Pinecone or Supabase for high-scale vector search<\/li>\n<li><strong>Privacy-first mode<\/strong> \u2014 Local Brain + Privacy Mode = zero external API calls<\/li>\n<\/ul>\n\n<h4>Why Choose Sentient AI?<\/h4>\n\n<p>Unlike basic chatbot plugins, Sentient AI offers:\n- Semantic search that understands meaning, not just keywords\n- Full site management through chat commands (Autopilot)\n- External AI agent integration via MCP (standard protocol)\n- Content optimization for AI-powered search engines (GEO)\n- Emotion-aware responses with automatic escalation\n- Transparent confidence scoring and source attribution\n- Privacy-first local processing with zero API costs\n- Multi-provider flexibility \u2014 use OpenAI, Claude, Gemini, or others<\/p>\n\n<h3>External Services<\/h3>\n\n<p>This plugin connects to external AI service providers to generate intelligent chatbot responses. You must configure API credentials for your chosen provider. <strong>Local Brain mode sends no data to external services.<\/strong><\/p>\n\n<h3>OpenAI<\/h3>\n\n<ul>\n<li><strong>Service Purpose<\/strong>: Provides AI-powered responses through OpenAI's GPT models and Assistants API<\/li>\n<li><strong>Data Sent<\/strong>: User queries, conversation history, and your configured assistant context<\/li>\n<li><strong>When Data is Sent<\/strong>: When a user submits a question that doesn't match an existing FAQ<\/li>\n<li><strong>API Endpoints Used<\/strong>: https:\/\/api.openai.com\/v1\/chat\/completions, https:\/\/api.openai.com\/v1\/threads, https:\/\/api.openai.com\/v1\/assistants<\/li>\n<li><strong>Terms of Service<\/strong>: https:\/\/openai.com\/terms<\/li>\n<li><strong>Privacy Policy<\/strong>: https:\/\/openai.com\/privacy<\/li>\n<\/ul>\n\n<h3>Claude (Anthropic)<\/h3>\n\n<ul>\n<li><strong>Service Purpose<\/strong>: Provides AI-powered responses using Anthropic's Claude models<\/li>\n<li><strong>Data Sent<\/strong>: User queries and conversation history<\/li>\n<li><strong>When Data is Sent<\/strong>: When a user submits a question that doesn't match an existing FAQ<\/li>\n<li><strong>API Endpoints Used<\/strong>: https:\/\/api.anthropic.com\/v1\/messages<\/li>\n<li><strong>Terms of Service<\/strong>: https:\/\/www.anthropic.com\/legal\/consumer-terms<\/li>\n<li><strong>Privacy Policy<\/strong>: https:\/\/www.anthropic.com\/legal\/privacy<\/li>\n<\/ul>\n\n<h3>Google Gemini<\/h3>\n\n<ul>\n<li><strong>Service Purpose<\/strong>: Provides AI-powered responses using Google's Gemini models<\/li>\n<li><strong>Data Sent<\/strong>: User queries and conversation history<\/li>\n<li><strong>When Data is Sent<\/strong>: When a user submits a question that doesn't match an existing FAQ<\/li>\n<li><strong>API Endpoints Used<\/strong>: https:\/\/generativelanguage.googleapis.com\/v1beta\/models\/{model}:generateContent<\/li>\n<li><strong>Terms of Service<\/strong>: https:\/\/policies.google.com\/terms<\/li>\n<li><strong>Privacy Policy<\/strong>: https:\/\/policies.google.com\/privacy<\/li>\n<\/ul>\n\n<h3>OpenRouter<\/h3>\n\n<ul>\n<li><strong>Service Purpose<\/strong>: Provides access to multiple AI models through a unified API<\/li>\n<li><strong>Data Sent<\/strong>: User queries, conversation history, and FAQ context<\/li>\n<li><strong>When Data is Sent<\/strong>: When a user submits a question that doesn't match an existing FAQ<\/li>\n<li><strong>API Endpoints Used<\/strong>: https:\/\/openrouter.ai\/api\/v1\/chat\/completions<\/li>\n<li><strong>Terms of Service<\/strong>: https:\/\/openrouter.ai\/terms<\/li>\n<li><strong>Privacy Policy<\/strong>: https:\/\/openrouter.ai\/privacy<\/li>\n<\/ul>\n\n<h3>Hugging Face<\/h3>\n\n<ul>\n<li><strong>Service Purpose<\/strong>: Provides access to open-source AI models<\/li>\n<li><strong>Data Sent<\/strong>: User queries and conversation history<\/li>\n<li><strong>When Data is Sent<\/strong>: When a user submits a question that doesn't match an existing FAQ<\/li>\n<li><strong>API Endpoints Used<\/strong>: https:\/\/api-inference.huggingface.co\/models\/{model}<\/li>\n<li><strong>Terms of Service<\/strong>: https:\/\/huggingface.co\/terms-of-service<\/li>\n<li><strong>Privacy Policy<\/strong>: https:\/\/huggingface.co\/privacy<\/li>\n<\/ul>\n\n<!--section=installation-->\n<ol>\n<li>Upload the <code>sentient-ai<\/code> folder to <code>\/wp-content\/plugins\/<\/code><\/li>\n<li>Activate the plugin from the <strong>Plugins<\/strong> menu<\/li>\n<li>Navigate to <strong>Sentient AI \u2192 Settings<\/strong> to configure<\/li>\n<li>Select your AI provider and enter your API key in the <strong>AI Providers<\/strong> tab<\/li>\n<li>Enable the chatbot in the <strong>General<\/strong> tab<\/li>\n<li>Customize appearance and behavior in the <strong>Widget<\/strong> and <strong>Features<\/strong> tabs<\/li>\n<li>Place <code>[sentient_ai_chat]<\/code> on any page, or use the floating widget<\/li>\n<\/ol>\n\n<!--section=faq-->\n<dl>\n<dt id=\"can%20this%20work%20without%20an%20api%20key%3F\"><h3>Can this work without an API key?<\/h3><\/dt>\n<dd><p>Yes. The browser-based FAQ matcher and Local Brain feature answer common questions using your FAQ database without any API calls. For AI-generated responses beyond existing FAQs, an API key from a supported provider is required.<\/p><\/dd>\n<dt id=\"which%20ai%20providers%20are%20supported%3F\"><h3>Which AI providers are supported?<\/h3><\/dt>\n<dd><p>OpenAI (GPT-4o, GPT-4, GPT-3.5), Claude by Anthropic, Google Gemini, OpenRouter (multi-model access), and Hugging Face. You can switch between providers at any time.<\/p><\/dd>\n<dt id=\"how%20does%20the%20semantic%20vector%20search%20work%3F\"><h3>How does the semantic vector search work?<\/h3><\/dt>\n<dd><p>The Vector Database (v2.8.0) converts your content into mathematical embeddings and stores them for similarity search. The Local MySQL engine works on any shared hosting using standard WordPress tables. For higher scale, Pinecone and Supabase cloud engines handle millions of vectors with SOC 2\/GDPR compliance.<\/p><\/dd>\n<dt id=\"which%20vector%20engine%20should%20i%20choose%3F\"><h3>Which vector engine should I choose?<\/h3><\/dt>\n<dd><p>For shared hosting with under 10,000 posts, the Local MySQL engine works without any additional setup. For larger sites, Pinecone or Supabase offer free tiers and enterprise-grade scalability.<\/p><\/dd>\n<dt id=\"what%20is%20the%20mcp%20server%3F\"><h3>What is the MCP Server?<\/h3><\/dt>\n<dd><p>The MCP Server implements the Model Context Protocol, a standard for connecting AI agents to external systems. It allows tools like Claude Desktop, Cursor, or custom AI agents to interact with your WordPress site \u2014 querying the chatbot, searching FAQs, managing content, and accessing analytics \u2014 all authenticated via API key.<\/p><\/dd>\n<dt id=\"how%20does%20the%20geo%20scanner%20help%20my%20content%3F\"><h3>How does the GEO Scanner help my content?<\/h3><\/dt>\n<dd><p>Generative Engine Optimization (GEO) ensures your content is cited by AI-powered search engines. The scanner analyzes each post across 10 factors \u2014 structured data, FAQ sections, citations, statistics, author expertise, content structure, and more \u2014 providing a score (0-100) with actionable suggestions and one-click fixes.<\/p><\/dd>\n<dt id=\"does%20this%20work%20with%20woocommerce%3F\"><h3>Does this work with WooCommerce?<\/h3><\/dt>\n<dd><p>Yes. The chatbot supports product lookup, order status checking, recommendations, and cart information. WooCommerce data is accessible through chat and is included in the Autopilot's site management capabilities.<\/p><\/dd>\n<dt id=\"is%20my%20data%20sent%20to%20external%20services%3F\"><h3>Is my data sent to external services?<\/h3><\/dt>\n<dd><p>Only when you explicitly configure an AI provider API key and a user query requires AI-generated response. FAQ-matched queries, Local Brain responses, and Privacy Mode interactions never leave your server. The plugin holds no data on its own \u2014 you control all API keys and provider choices.<\/p><\/dd>\n<dt id=\"can%20i%20customize%20the%20chatbot%20appearance%3F\"><h3>Can I customize the chatbot appearance?<\/h3><\/dt>\n<dd><p>Yes. Six preset themes (Indigo, Ocean, Emerald, Rose, Amber, Slate) plus custom color pickers, border radius adjustment, and a live preview in settings. You can also configure quick replies, canned responses, and a pre-chat form.<\/p><\/dd>\n<dt id=\"what%20is%20wordpress%20autopilot%3F\"><h3>What is WordPress Autopilot?<\/h3><\/dt>\n<dd><p>An administrator-only AI agent that executes WordPress tasks through the chat interface. Supported commands include creating posts and pages, listing content, checking for plugin\/theme\/core updates, finding broken images, clearing cache, and retrieving site statistics. All actions are logged for review.<\/p><\/dd>\n\n<\/dl>\n\n<!--section=changelog-->\n<h4>2.10.1<\/h4>\n\n<ul>\n<li><strong>WooCommerce Deep Integration<\/strong> \u2014 HPOS, product vectorization, real-time webhooks<\/li>\n<li>HPOS (High-Performance Order Storage) support \u2014 reads orders from custom wc_orders tables when enabled, auto-falls back to legacy wp_posts<\/li>\n<li>get_order_stats_hpos() queries either HPOS tables or legacy storage based on what's active<\/li>\n<li>hpos_enabled() detection method for plugin-wide awareness<\/li>\n<li>Product vectorization \u2014 auto-generates rich embeddings from product title, description, attributes, categories, tags, reviews, FAQs, variations, and upsells<\/li>\n<li>on_product_save() hooks into woocommerce_new_product and woocommerce_update_product<\/li>\n<li>reindex_all_products() bulk reindex with woocommerce_product_import_end integration<\/li>\n<li>Real-time WooCommerce webhooks \u2014 REST endpoint at \/wp-json\/sentientai-woo\/v1\/webhook with HMAC signature verification<\/li>\n<li>8 webhook events: order created, completed, cancelled; product updated; stock status changed; review created; low stock; no stock<\/li>\n<li>Event data includes structured payloads with formatted messages for logging<\/li>\n<li>Product webhooks trigger automatic re-vectorization<\/li>\n<li>Secret key configuration with optional signature validation<\/li>\n<li>All events logged to query log with source='webhook'<\/li>\n<li>New WooCommerce Deep Integration card in Features tab with 4 toggles and HPOS\/vectorization info<\/li>\n<li>Fixed: $wpdb global used before declaration in handle_webhook_event()<\/li>\n<li>Fixed: Missing register_setting() for sentient_ai_woo_webhooks_enabled and sentient_ai_woo_webhook_secret<\/li>\n<li>Added: sentient_ai_woo_webhooks_enabled to checkbox preservation array<\/li>\n<li>Added: 72 test cases covering all WooCommerce integration methods<\/li>\n<li><strong>Conversational Commerce Engine<\/strong> \u2014 AI shopping assistant with Vibe Search, Visual Shop, Gift Concierge<\/li>\n<li>Vibe Search: natural language product matching via Vector DB with tokenized match reasons<\/li>\n<li>Visual Shop: image URL \u2192 AI description \u2192 visual product matching with domain security<\/li>\n<li>Gift Concierge: 5 guided questions \u2192 personalized gift guides with budget\/personality scoring<\/li>\n<li>Admin toggles for each feature + allowed image domains list<\/li>\n<li>Fixed: Vibe search used get_post() instead of wc_get_product() for vector results<\/li>\n<li>Fixed: Visual Shop didn't check WooCommerce is active before loading products<\/li>\n<li>Fixed: Match reasons checked full query against product name instead of individual tokens<\/li>\n<li>Fixed: Gift Concierge questions missing translation wrappers<\/li>\n<li>Fixed: Extra PHP bracket in Commerce Engine feature card array<\/li>\n<\/ul>\n\n<h4>2.8.0<\/h4>\n\n<ul>\n<li>New: Vector Database with two-tier semantic search \u2014 Local MySQL (shared hosting) and Pinecone\/Supabase cloud engines<\/li>\n<li>New: Auto-generated embeddings for posts, pages, and FAQs with OpenAI API or built-in hash fallback<\/li>\n<li>New: Semantic search integrated into chatbot responses for meaning-based content matching<\/li>\n<li>New: Admin settings page with engine selector, cloud provider configuration, and index status dashboard<\/li>\n<li>Combined 2.7.0 features: MCP Server (8 tools, SSE transport, API key auth, CORS headers)<\/li>\n<li>Combined 2.7.0 features: GEO Scanner (10-factor content analysis, scoring dashboard, one-click schema fixes)<\/li>\n<li>Combined 2.7.0 features: Browser-based FAQ matcher with keyword and title matching<\/li>\n<li>Fixed: Settings reset when saving across tabs (Enable Chatbot, Pre-Chat Form, role limits)<\/li>\n<li>Fixed: Pre-Chat Form data not persisting across page loads (sessionStorage)<\/li>\n<li>Fixed: Welcome message not displaying when chat opens<\/li>\n<li>Fixed: Role limit field blocking form submission when feature is disabled<\/li>\n<li>Fixed: SSE endpoint infinite loop (timeout added)<\/li>\n<li>Fixed: Missing content format in MCP manage_wp tool<\/li>\n<li>Fixed: Unhelpful error message when no API key configured<\/li>\n<li>Fixed: FAQ matching skipped when conversation history exists<\/li>\n<li>Chore: Added Help tab with complete feature documentation<\/li>\n<\/ul>\n\n<h4>2.7.0<\/h4>\n\n<ul>\n<li><strong>MCP Server<\/strong> \u2014 Model Context Protocol support for AI agent integration<\/li>\n<li>8 tools: chat, FAQ search\/list\/create, contacts, stats, low confidence, WordPress management<\/li>\n<li>3 resources: FAQ database, usage stats, contacts<\/li>\n<li>2 prompts: site overview, FAQ improvement<\/li>\n<li>API key authentication, SSE transport, CORS, rate limiting<\/li>\n<li><strong>GEO Scanner<\/strong> \u2014 10-factor content analysis for AI search visibility<\/li>\n<li>Factors: content length, structured data, FAQs, citations, statistics, E-E-A-T, structure, meta, lists, titles<\/li>\n<li>Scoring dashboard with auto-fix actions<\/li>\n<li><strong>Browser-Based FAQ Matcher<\/strong> \u2014 Local FAQ search without API key<\/li>\n<li><strong>Bug fixes<\/strong> \u2014 Multi-tab settings persistence, pre-chat form stability, welcome message display<\/li>\n<li><strong>Help tab<\/strong> \u2014 Complete feature reference with documentation<\/li>\n<\/ul>\n\n<h4>2.6.0<\/h4>\n\n<ul>\n<li><strong>Security Hardening<\/strong> \u2014 Remediated Assistant ID leak, added output sanitization<\/li>\n<li><strong>Design Refresh<\/strong> \u2014 Modernized UI with CSS variables, improved SVG rendering<\/li>\n<li><strong>Bug Fixes<\/strong> \u2014 Resolved ReferenceError, history persistence, transient counting, approval flow<\/li>\n<\/ul>\n\n<h4>2.4.0<\/h4>\n\n<ul>\n<li><strong>WooCommerce Deep Integration<\/strong> \u2014 Product lookup by name\/SKU, order status, recommendations, cart info<\/li>\n<li>Performance: FAQ query caching, Options_Cache helper<\/li>\n<\/ul>\n\n<h4>2.3.0<\/h4>\n\n<ul>\n<li><strong>Widget Branding &amp; Theming<\/strong> \u2014 6 themes, custom colors, border radius, live preview<\/li>\n<li><strong>Prompt Injection Protection<\/strong> \u2014 20+ injection pattern detection<\/li>\n<\/ul>\n\n<h4>2.2.0<\/h4>\n\n<ul>\n<li><strong>Local Brain<\/strong> \u2014 Fuse.js-powered fuzzy FAQ search in the browser, zero API costs, offline support<\/li>\n<li><strong>Privacy Mode<\/strong> \u2014 Restrict all processing to local database<\/li>\n<\/ul>\n\n<h4>2.1.0<\/h4>\n\n<ul>\n<li><strong>WordPress Autopilot<\/strong> \u2014 10 commands: updates, broken images, posts, security, cache, stats, health<\/li>\n<\/ul>\n\n<h4>2.0.0<\/h4>\n\n<ul>\n<li><strong>Sentient Memory<\/strong> \u2014 Topic clustering, feedback tracking, auto-FAQ generation, learning dashboard<\/li>\n<\/ul>\n\n<h4>1.4.0<\/h4>\n\n<ul>\n<li><strong>Empathy Engine<\/strong> \u2014 Emotion detection and dynamic tone adaptation<\/li>\n<\/ul>\n\n<h4>1.3.0<\/h4>\n\n<ul>\n<li><strong>Glass Box Transparency<\/strong> \u2014 Confidence scoring and source attribution<\/li>\n<\/ul>\n\n<h4>1.2.0<\/h4>\n\n<ul>\n<li>Multi-turn conversation context and server-side history<\/li>\n<\/ul>\n\n<h4>1.1.1<\/h4>\n\n<ul>\n<li>Security and performance hotfixes<\/li>\n<\/ul>\n\n<h4>1.1.0<\/h4>\n\n<ul>\n<li>Session-based chat history, TXT export, configurable position<\/li>\n<\/ul>\n\n<h4>1.0.0<\/h4>\n\n<ul>\n<li>Initial release with multi-AI support<\/li>\n<\/ul>","raw_excerpt":"A feature-rich AI chatbot for WordPress with semantic vector search, WordPress Autopilot, local browser-based AI, and MCP Server integration.","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/fi.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin\/254017","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fi.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin"}],"about":[{"href":"https:\/\/fi.wordpress.org\/plugins\/wp-json\/wp\/v2\/types\/plugin"}],"replies":[{"embeddable":true,"href":"https:\/\/fi.wordpress.org\/plugins\/wp-json\/wp\/v2\/comments?post=254017"}],"author":[{"embeddable":true,"href":"https:\/\/fi.wordpress.org\/plugins\/wp-json\/wporg\/v1\/users\/maidulcu"}],"wp:attachment":[{"href":"https:\/\/fi.wordpress.org\/plugins\/wp-json\/wp\/v2\/media?parent=254017"}],"wp:term":[{"taxonomy":"plugin_section","embeddable":true,"href":"https:\/\/fi.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_section?post=254017"},{"taxonomy":"plugin_tags","embeddable":true,"href":"https:\/\/fi.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_tags?post=254017"},{"taxonomy":"plugin_category","embeddable":true,"href":"https:\/\/fi.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_category?post=254017"},{"taxonomy":"plugin_contributors","embeddable":true,"href":"https:\/\/fi.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_contributors?post=254017"},{"taxonomy":"plugin_business_model","embeddable":true,"href":"https:\/\/fi.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_business_model?post=254017"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}