Data Ingestion & Knowledge Sources
Supported formats – PDFs and website crawling only (max 2,000 pages)Plan limits – Team: 10 files/3 sites, Business: 30 files/10 sites⚠️ NO DOCX, TXT, CSV, Excel – No audio, video, code files (vs 1,400+ formats)
⚠️ NO cloud storage sync – No Google Drive, Dropbox, OneDrive, Notion, Confluence
✅ Auto-Indexing – Points at files, indexes unstructured data automatically without manual setup✅ Auto-Sync – Connected repositories sync automatically, document changes reflected almost instantlyFile Formats – Supports PDF, DOCX, PPT, TXT and common enterprise formats⚠️ Limited Scope – No website crawling or YouTube ingestion, narrower than CustomGPTEnterprise Scale – Handles large corporate data sets, exact limits not published
1,400+ file formats – PDF, DOCX, Excel, PowerPoint, Markdown, HTML + auto-extraction from ZIP/RAR/7Z archivesWebsite crawling – Sitemap indexing with configurable depth for help docs, FAQs, and public contentMultimedia transcription – AI Vision, OCR, YouTube/Vimeo/podcast speech-to-text built-inCloud integrations – Google Drive, SharePoint, OneDrive, Dropbox, Notion with auto-syncKnowledge platforms – Zendesk, Freshdesk, HubSpot, Confluence, Shopify connectorsMassive scale – 60M words (Standard) / 300M words (Premium) per bot with no performance degradation
Messaging platforms – Website, Facebook, WhatsApp, Apple Messages, Telegram, SMS, email200+ marketplace integrations – Zapier (5,000+ apps), HubSpot, Salesforce, Zendesk, IntercomE-commerce platforms – Shopify, WooCommerce, BigCommerce native plugins✅ Custom integrations – Webhooks with JSON payloads, 10s response timeout
⚠️ Standalone Only – Own chat/search interface, not a "deploy everywhere" platform⚠️ No External Channels – No Slack bot, Zapier connector, or public APIWeb/Desktop UI – Users interact through Pyx's interface, minimal third-party chat synergyCustom Integration – Deeper integrations require custom dev work or future updates
Website embedding – Lightweight JS widget or iframe with customizable positioningCMS plugins – WordPress, WIX, Webflow, Framer, SquareSpace native support5,000+ app ecosystem – Zapier connects CRMs, marketing, e-commerce toolsMCP Server – Integrate with Claude Desktop, Cursor, ChatGPT, WindsurfOpenAI SDK compatible – Drop-in replacement for OpenAI API endpointsLiveChat + Slack – Native chat widgets with human handoff capabilities
200+ Integration Ecosystem ( Core Differentiator)
✅ Mature marketplace – 200+ pre-built integrations after 20+ years development
✅ Enterprise CRM depth – Deep Salesforce, HubSpot, Zendesk, Intercom integrations
✅ E-commerce validated – Official Shopify/WooCommerce/BigCommerce plugins
✅ Webhook flexibility – JSON payloads, 10s timeouts for custom workflows (8/10 differentiator)
N/A
N/A
Agent Chat A P I v3.5 ( Differentiator)
Dual transport – REST API and WebSocket (RTM) for real-time communicationOfficial SDKs – JavaScript/Node.js, iOS (Swift), Android (Kotlin), Customer SDKOAuth 2.1 PKCE – Modern auth plus Personal Access Tokens⚠️ Rate limits – 180 requests/min may constrain high-volume apps
⚠️ Chat ops focus – No RAG APIs for semantic search or embedding management
N/A
N/A
AI Reply Suggestions – Context-based response recommendations from knowledge sourcesText Enhancement – Grammar correction and tone polishing before sendingAI Insights – Analyzes 1,000+ queries in 30s for trends⚠️ NO anti-hallucination – No citation attribution or source tracing
⚠️ NO Agent Capabilities – No autonomous agents, tool calling, or multi-agent orchestrationConversational Search Only – Context-aware dialogue for Q&A, not agentic or autonomous behaviorBasic RAG Architecture – Standard retrieval without function calling, tool use, or workflows⚠️ No External Actions – Cannot invoke APIs, execute code, query databases, or interact externallyInternal Knowledge Focus – Employee Q&A about documents, not task automation or workflows
Custom AI Agents – Autonomous GPT-4/Claude agents for business tasksMulti-Agent Systems – Specialized agents for support, sales, knowledgeMemory & Context – Persistent conversation history across sessionsTool Integration – Webhooks + 5,000 Zapier apps for automationContinuous Learning – Auto re-indexing without manual retraining
Chat Bot Automation ( Separate Product)
Visual builder – Drag-and-drop no-code chatbot with NLPProprietary engine – Internal NLP, doesn't use OpenAI/Bard/Bing⚠️ Additional cost – $52/month on top of LiveChat subscription
⚠️ NO LLM selection – Proprietary only, no GPT-4/Claude/Gemini access
N/A
N/A
Widget Customization & White- Labeling
Live editor – Theme presets, custom hex colors, logo uploads, positioningWCAG 2.1 AA – Accessibility with screen readers, keyboard navigationMobile responsive – Device-specific settings and hiding options⚠️ White-label Enterprise only – Requires custom pricing, minimum 5 seats
N/A
N/A
⚠️ NO model selection – Proprietary AI engine only
⚠️ NO GPT-4, Claude, Gemini – Cannot choose LLM providers
⚠️ NO BYOLLM – No custom models or fine-tuning
⚠️ Opaque processing – Architecture and training data not documented (3/10 flexibility)
⚠️ Undisclosed Model – Likely GPT-3.5/GPT-4 but exact model not publicly documented⚠️ No Model Selection – Cannot switch LLMs or configure speed vs accuracy tradeoffs⚠️ Single Configuration – Every query uses same model, no toggles or fine-tuningClosed Architecture – Model details, context window, capabilities hidden from users intentionally
GPT-5.1 models – Latest thinking models (Optimal & Smart variants)GPT-4 series – GPT-4, GPT-4 Turbo, GPT-4o availableClaude 4.5 – Anthropic's Opus available for EnterpriseAuto model routing – Balances cost/performance automaticallyZero API key management – All models managed behind the scenes
Developer Experience ( A P I & S D Ks)
Agent Chat API v3.5 – REST and WebSocket with OAuth 2.1 PKCEMobile SDKs – iOS (Swift, iOS 15.6+), Android (Kotlin via Gradle)✅ Strong documentation – Postman collections, tutorials, Discord community
⚠️ NO Python SDK – JavaScript/mobile only, limits backend integration
⚠️ No API – No open API or SDKs, everything through Pyx interface⚠️ No Embedding – Cannot integrate into other apps or call programmaticallyClosed Ecosystem – No GitHub examples, community plug-ins, or extensibility optionsTurnkey Only – Great for ready-made tool, limits deep customization or extensions
REST API – Full-featured for agents, projects, data ingestion, chat queriesPython SDK – Open-source customgpt-client with full API coveragePostman collections – Pre-built requests for rapid prototypingWebhooks – Real-time event notifications for conversations and leadsOpenAI compatible – Use existing OpenAI SDK code with minimal changes
R A G Implementation & Accuracy
⚠️ NOT RAG-as-a-Service – No vector database, embeddings, retrieval pipeline
⚠️ NO chunking/embedding controls – Size, overlap, model selection not exposed
⚠️ NO hybrid search – No keyword + semantic combination
⚠️ NO anti-hallucination – No citations, source verification (2/10 RAG platform)
N/A
N/A
Real-time delivery – Sub-second message delivery, praised for reliabilityScalability – 37,000+ businesses, enterprise customers (Adobe, PayPal, IKEA)⚠️ NO accuracy benchmarks – No published AI retrieval metrics
⚠️ Operational focus – Metrics for queue times, agent response, not AI accuracy
Real-Time Answers – Serves accurate responses from internal documents, sparse public benchmarksAuto-Sync Freshness – Connected repositories keep retrieval context always current automatically⚠️ Limited Transparency – No anti-hallucination metrics or advanced re-ranking details publishedCompetitive RAG – Likely comparable to standard GPT-based systems on relevance control
Sub-second responses – Optimized RAG with vector search and multi-layer cachingBenchmark-proven – 13% higher accuracy, 34% faster than OpenAI Assistants APIAnti-hallucination tech – Responses grounded only in your provided contentOpenGraph citations – Rich visual cards with titles, descriptions, images99.9% uptime – Auto-scaling infrastructure handles traffic spikes
✅ Seven certifications – SOC 2, GDPR, HIPAA, ISO 27001, PCI DSS, FedRAMP, CSA Star
Encryption – TLS transit, AES-256 at restData residency – EU (Poland) compliance with account isolation⚠️ SSO/SAML Enterprise only – Significant gap for mid-market identity management
✅ GDPR Compliance – Germany-based, implicit EU data protection and regional sovereignty✅ Enterprise Privacy – Data isolated per customer, encrypted in transit and rest✅ No Model Training – Customer data not used for external LLM training✅ Role-Based Access – Built-in controls, admins set document visibility per role⚠️ Limited Certifications – On-prem or SOC 2/ISO 27001/HIPAA not publicly documented
SOC 2 Type II + GDPR – Third-party audited complianceEncryption – 256-bit AES at rest, SSL/TLS in transitAccess controls – RBAC, 2FA, SSO, domain allowlistingData isolation – Never trains on your data
Full Compliance Portfolio ( Core Differentiator)
✅ Seven certifications – SOC 2, GDPR, HIPAA, ISO 27001, PCI DSS, FedRAMP, CSA Star
✅ FedRAMP unique – Rare federal authorization enables government contracts
✅ PCI DSS masking – Built-in payment card protection for financial services
✅ HIPAA BAA – Business Associate Agreement for healthcare compliance (9/10 differentiator)
N/A
N/A
Observability & Monitoring
Real-time monitoring – Agent status, queue depth, visitor activity dashboardsChat metrics – Volume, missed chats, response times, agent performance, CSATStaffing predictions – AI scheduling optimization (Business+ plans)⚠️ NO AI metrics – No retrieval accuracy, semantic search, hallucination monitoring
Basic Stats – User activity, query counts, top-referenced documents for admins⚠️ No Deep Analytics – No conversation analytics dashboards or real-time loggingAdoption Tracking – Useful for usage monitoring, lighter insights than full suitesSet-and-Forget – Minimal monitoring overhead, contact support for issues
Real-time dashboard – Query volumes, token usage, response timesCustomer Intelligence – User behavior patterns, popular queries, knowledge gapsConversation analytics – Full transcripts, resolution rates, common questionsExport capabilities – API export to BI tools and data warehouses
Starter – $20/agent/month, 60-day history, 1 userTeam – $41/agent/month, unlimited history, 10 files/3 sitesBusiness – $59/agent/month, staffing predictions, 30 files/10 sitesEnterprise – Custom pricing, min 5 seats, SSO/SAML, white-label, HIPAA⚠️ Cost escalation – 10 agents + ChatBot = $642/month ($7,704/year)
Seat-Based Pricing – ~$30 per user per month, predictable monthly costs✅ Cost-Effective Small Teams – Affordable for teams under 50 users⚠️ Large Team Costs – 100 users = $3,000/month, can scale expensivelyUnlimited Content – Document/token limits not published, gated only by user seatsFree Trial + Enterprise – Hands-on trial available, custom pricing for large deployments
Standard: $99/mo – 60M words, 10 botsPremium: $449/mo – 300M words, 100 botsAuto-scaling – Managed cloud scales with demandFlat rates – No per-query charges
✅ 24/7 support – Live chat and email, consistently praised (4.5/5 G2, 4.6/5 Capterra)
Developer docs – Extensive at developers.livechat.com with Postman, tutorialsEnterprise SLA – Guaranteed response times on custom contractsCommon criticisms – Rising prices, per-agent scaling costs, fragmented ChatBot product
✅ Direct Support – Email, phone, chat with hands-on onboarding approach⚠️ No Open Community – Closed solution, no plug-ins or user-built extensionsInternal Roadmap – Product updates from Pyx only, no community marketplaceQuick Setup Focus – Emphasizes minimal admin overhead for internal knowledge search
Comprehensive docs – Tutorials, cookbooks, API referencesEmail + in-app support – Under 24hr response timePremium support – Dedicated account managers for Premium/EnterpriseOpen-source SDK – Python SDK, Postman, GitHub examples5,000+ Zapier apps – CRMs, e-commerce, marketing integrations
Additional Considerations
⚠️ Platform classification – Human-agent live chat with AI, NOT RAG-as-a-Service
✅ Primary strength – Customer support workflows with 200+ integrations, seven certifications
⚠️ Knowledge gap – PDFs/websites only, NO DOCX/CSV/Excel/audio/video/code files
⚠️ NO RAG infrastructure – No vector DB, embeddings, chunking, similarity thresholds
✅ No-Fuss Internal Search – Employees use without coding, simple deployment for teams⚠️ Not Public-Facing – Not ideal for customer chatbots or developer-heavy customizationSiloed Environment – Single AI search environment, not broad extensible platformSimpler Scope – Less flexible than CustomGPT, but faster setup for internal use
Time-to-value – 2-minute deployment vs weeks with DIYAlways current – Auto-updates to latest GPT modelsProven scale – 6,000+ organizations, millions of queriesMulti-LLM – OpenAI + Claude reduces vendor lock-in
Proprietary engine – Internal NLP, doesn't rely on OpenAI/Bard/Bing⚠️ NO LLM selection – Cannot choose GPT-4, Claude, Gemini
⚠️ Opaque architecture – Model training data, capabilities not documented
⚠️ NO BYOLLM – No model routing, fine-tuning, custom models (3/10 flexibility)
⚠️ Undisclosed LLM – Likely GPT-3.5/GPT-4 but model details not publicly documented⚠️ No Model Selection – Cannot switch LLMs or choose speed vs accuracy configurations⚠️ Opaque Architecture – Context window size and capabilities not exposed to usersSimplicity Focus – Hides technical complexity, users ask questions and get answers⚠️ No Fine-Tuning – Cannot customize model on domain data for specialized responses
OpenAI – GPT-5.1 (Optimal/Smart), GPT-4 seriesAnthropic – Claude 4.5 Opus/Sonnet (Enterprise)Auto-routing – Intelligent model selection for cost/performanceManaged – No API keys or fine-tuning required
⚠️ NOT RAG platform – No vector DB, embedding controls, retrieval pipeline
⚠️ Limited sources – PDFs and websites only (max 2,000 pages, 10-30 files)
⚠️ Human-agent focus – Agent workflows, not autonomous retrieval (2/10 RAG rating)
Conversational RAG – Context-aware search over enterprise documents with follow-up support✅ Auto-Sync – Repositories sync automatically, changes reflected almost instantlyDocument Formats – PDF, DOCX, PPT, TXT and common enterprise formats supported⚠️ No Advanced Controls – Chunking, embedding models, similarity thresholds not exposed⚠️ Limited Transparency – No citation metrics or anti-hallucination details publishedClosed System – Optimized for internal Q&A, limited visibility into retrieval architecture
GPT-4 + RAG – Outperforms OpenAI in independent benchmarksAnti-hallucination – Responses grounded in your content onlyAutomatic citations – Clickable source links in every responseSub-second latency – Optimized vector search and cachingScale to 300M words – No performance degradation at scale
✅ Customer support – Live chat for 37,000+ businesses with AI agent augmentation
✅ E-commerce – Shopify/WooCommerce/BigCommerce native integrations
✅ Multi-channel – Website, Facebook, WhatsApp, Apple Messages, Telegram, SMS
⚠️ NOT suitable for – Autonomous knowledge retrieval, programmatic document search
✅ Internal Knowledge Search – Employees asking questions about company documents and policies✅ Team Onboarding – New hires finding information without bothering colleagues✅ Policy Lookup – HR, compliance, operational procedure retrieval for staff✅ Small European Teams – GDPR-compliant internal search with EU data residency⚠️ NOT SUITABLE FOR – Public chatbots, customer support, API integrations, multi-channel deployment
Customer support – 24/7 AI handling common queries with citationsInternal knowledge – HR policies, onboarding, technical docsSales enablement – Product info, lead qualification, educationDocumentation – Help centers, FAQs with auto-crawlingE-commerce – Product recommendations, order assistance
✅ Seven certifications – SOC 2, GDPR, HIPAA, ISO 27001, PCI DSS, FedRAMP, CSA Star
✅ Data privacy – Customer data never used for training, zero-retention policies
Encryption – TLS transit, AES-256 at rest, regional data residency⚠️ HIPAA/SSO Enterprise only – Min 5 seats ($6,000/year minimum)
✅ GDPR Compliance – Germany-based with implicit EU data protection compliance✅ German Data Residency – EU storage location for regional data sovereignty requirements✅ Enterprise Privacy – Customer data isolated, encrypted in transit and at rest✅ Role-Based Access – Built-in controls, admins set document visibility per user⚠️ Limited Certifications – SOC 2, ISO 27001, HIPAA not publicly documented
SOC 2 Type II + GDPR – Regular third-party audits, full EU compliance256-bit AES encryption – Data at rest; SSL/TLS in transitSSO + 2FA + RBAC – Enterprise access controls with role-based permissionsData isolation – Never trains on customer dataDomain allowlisting – Restrict chatbot to approved domains
Starter – $20/agent/month, 60-day history, 1 userTeam – $41/agent/month, unlimited history, 400 users, AI featuresBusiness – $59/agent/month, staffing predictions, full AI featuresEnterprise – Custom pricing (min 5 seats), SSO/SAML, white-label, HIPAA⚠️ Cost escalation – Per-agent model criticized for scaling vs project pricing
Seat-Based Pricing – ~$30 per user per month✅ Small Team Value – Affordable for teams under 50 users, predictable costs⚠️ Scalability Cost – 100 users = $3,000/month, expensive for large organizationsUnlimited Content – No published document limits, gated only by user seatsFree Trial + Enterprise – Evaluation available, custom pricing for volume discounts
Standard: $99/mo – 10 chatbots, 60M words, 5K items/botPremium: $449/mo – 100 chatbots, 300M words, 20K items/botEnterprise: Custom – SSO, dedicated support, custom SLAs7-day free trial – Full Standard access, no chargesFlat-rate pricing – No per-query charges, no hidden costs
✅ 24/7 support – Live chat/email, consistently praised (4.5/5 G2, 4.6/5 Capterra)
Developer docs – Extensive at developers.livechat.com with Postman, tutorialsEnterprise SLA – Guaranteed response times, uptime commitmentsSDK support – JavaScript, iOS (Swift), Android (Kotlin), Customer SDK
✅ Direct Support – Email, phone, chat with hands-on onboarding approach✅ Quick Deployment – Minimal admin overhead, connect sources and start asking questions⚠️ No Open Community – Closed solution, no plug-ins or user extensions⚠️ No Developer Docs – No API documentation or programmatic access guidesInternal Roadmap – Updates from Pyx only, no user-contributed features
Documentation hub – Docs, tutorials, API referencesSupport channels – Email, in-app chat, dedicated managers (Premium+)Open-source – Python SDK, Postman, GitHub examplesCommunity – User community + 5,000 Zapier integrations
Limitations & Considerations
⚠️ NOT RAG platform – Human-agent live chat, not autonomous retrieval (2/10 RAG)
⚠️ Limited formats – PDFs/websites only, NO DOCX/CSV/Excel/audio/video/code
⚠️ NO LLM flexibility – Proprietary engine only, no GPT-4/Claude/Gemini
⚠️ Fragmented product – ChatBot requires separate $52/month purchase
⚠️ Cost scaling – Per-agent pricing criticized, 10 agents = $642/month
⚠️ No Public API – Cannot embed or call programmatically, standalone UI only⚠️ No Messaging Integrations – No Slack, Teams, WhatsApp or chat platform connectors⚠️ Limited Branding – Minimal customization, not white-label solution for public deployment⚠️ No Advanced Controls – Cannot configure RAG parameters, model selection, retrieval strategies⚠️ Seat-Based Scaling – Expensive for large orgs vs usage-based pricing models✅ Best For – Small European teams (<50 users) prioritizing simplicity and GDPR over flexibility
Managed service – Less control over RAG pipeline vs build-your-ownModel selection – OpenAI + Anthropic only; no Cohere, AI21, open-sourceReal-time data – Requires re-indexing; not ideal for live inventory/pricesEnterprise features – Custom SSO only on Enterprise plan
N/A
Conversational Search – Context-aware Q&A over enterprise documents with follow-up questions⚠️ Internal Focus – Designed for knowledge management, no lead capture or human handoffMulti-Language – Likely supports multiple languages, though not a headline feature⚠️ Basic Analytics – Stores chat history, fewer business insights than customer-facing tools
✅ #1 accuracy – Median 5/5 in independent benchmarks, 10% lower hallucination than OpenAI✅ Source citations – Every response includes clickable links to original documents✅ 93% resolution rate – Handles queries autonomously, reducing human workload✅ 92 languages – Native multilingual support without per-language config✅ Lead capture – Built-in email collection, custom forms, real-time notifications✅ Human handoff – Escalation with full conversation context preserved
N/A
⚠️ Minimal Branding – Logo/color tweaks only, designed as internal tool not white-label⚠️ No Embedding – Standalone interface, no domain-embed or widget options availablePyx UI Only – Look stays "Pyx AI" by design, public branding not supportedSecurity Focus – Emphasis on user management and access controls over theming
Full white-labeling included – Colors, logos, CSS, custom domains at no extra cost2-minute setup – No-code wizard with drag-and-drop interfacePersona customization – Control AI personality, tone, response style via pre-promptsVisual theme editor – Real-time preview of branding changesDomain allowlisting – Restrict embedding to approved sites only
Customization & Flexibility ( Behavior & Knowledge) N/A
✅ Auto-Sync Updates – Knowledge base updated without manual uploads or scheduling⚠️ No Persona Controls – AI voice stays neutral, no tone or behavior customization✅ Access Controls – Strong role-based permissions, admins set document visibility per userClosed Environment – Great for content updates, limited for AI behavior or deployment
Live content updates – Add/remove content with automatic re-indexingSystem prompts – Shape agent behavior and voice through instructionsMulti-agent support – Different bots for different teamsSmart defaults – No ML expertise required for custom behavior
No- Code Interface & Usability N/A
✅ Straightforward UI – Users log in, ask questions, get answers without coding✅ No-Code Admin – Admins connect data sources, Pyx indexes automaticallyMinimal Customization – UI stays consistent and uncluttered by designInternal Q&A Hub – Perfect for employee use, not external embedding or branding
2-minute deployment – Fastest time-to-value in the industryWizard interface – Step-by-step with visual previewsDrag-and-drop – Upload files, paste URLs, connect cloud storageIn-browser testing – Test before deploying to productionZero learning curve – Productive on day one
N/A
Market Position – Turnkey internal knowledge search (Germany), not embeddable chatbot platformTarget Customers – Small-mid European teams needing GDPR compliance and simple deploymentKey Competitors – Glean, Guru, Notion AI; not customer-facing chatbots like CustomGPT✅ Advantages – Simple scope, auto-sync, GDPR compliance, ~$30/user/month predictable pricing⚠️ Use Case Fit – Perfect for <50 user teams, not API integrations or public chatbots
Market position – Leading RAG platform balancing enterprise accuracy with no-code usability. Trusted by 6,000+ orgs including Adobe, MIT, Dropbox.Key differentiators – #1 benchmarked accuracy • 1,400+ formats • Full white-labeling included • Flat-rate pricingvs OpenAI – 10% lower hallucination, 13% higher accuracy, 34% fastervs Botsonic/Chatbase – More file formats, source citations, no hidden costsvs LangChain – Production-ready in 2 min vs weeks of development
R A G-as-a- Service Assessment N/A
⚠️ NOT TRUE RAG-AS-A-SERVICE – Standalone internal app, not API-accessible RAG platformTurnkey Application – Self-contained Q&A tool vs developer-accessible RAG infrastructure⚠️ No API Access – No REST API, SDKs, programmatic access unlike CustomGPT/VectaraClosed Application – Web/desktop interface only, cannot build custom applications on topSaaS vs RaaS – Software-as-a-Service (standalone app) NOT Retrieval-as-a-Service (API infrastructure)Best Comparison Category – Internal search tools (Glean, Guru), not developer RAG platforms
Platform type – TRUE RAG-AS-A-SERVICE with managed infrastructureAPI-first – REST API, Python SDK, OpenAI compatibility, MCP ServerNo-code option – 2-minute wizard deployment for non-developersHybrid positioning – Serves both dev teams (APIs) and business users (no-code)Enterprise ready – SOC 2 Type II, GDPR, WCAG 2.0, flat-rate pricing
Join the Discussion
Loading comments...