In this comprehensive guide, we compare Botpress and Tidio across various parameters including features, pricing, performance, and customer support to help you make the best decision for your business needs.
Overview
When choosing between Botpress and Tidio, understanding their unique strengths and architectural differences is crucial for making an informed decision. Both platforms serve the RAG (Retrieval-Augmented Generation) space but cater to different use cases and organizational needs.
Quick Decision Guide
Choose Botpress if: you value visual drag-and-drop builder with extensive code extensibility via execute code cards
Choose Tidio if: you value exceptional ease of use: 4.7/5 g2 rating with 253 'ease of use' and 161 'easy setup' mentions
About Botpress
Botpress is enterprise ai agent platform with visual bot building and omnichannel deployment. Enterprise AI agent platform with visual bot building, omnichannel deployment, and RAG capabilities. 750,000+ active bots processing 1 billion+ messages with extensive channel support and no-code/low-code development. Founded in 2016, headquartered in Montreal, Quebec, Canada, the platform has established itself as a reliable solution in the RAG space.
Overall Rating
85/100
Starting Price
Custom
About Tidio
Tidio is no-code customer service automation with claude 3-powered ai chatbots. Customer service automation platform with Claude 3-powered Lyro AI achieving 67-90% resolution rates. Founded 2013 by Tytus Gołąs (Poland), serves 300,000+ businesses including Pizza Hut, Decathlon, Casio. NOT a RAG-as-a-Service platform—optimized for SMB/e-commerce no-code chatbot building with exceptional ease of use (4.7/5 G2, 1,600+ reviews). SOC 2 Type II + GDPR certified. Critical gaps: NO programmatic knowledge API, NO LLM model selection (Claude-only), NO cloud storage integrations. $0-$2,999+/month with per-conversation billing ($0.50/Lyro chat). Founded in 2013, headquartered in San Francisco, CA (offices in Szczecin and Warsaw, Poland), the platform has established itself as a reliable solution in the RAG space.
Overall Rating
87/100
Starting Price
$29/mo
Key Differences at a Glance
In terms of user ratings, both platforms score similarly in overall satisfaction. From a cost perspective, Botpress starts at a lower price point. The platforms also differ in their primary focus: Chatbot Platform versus Customer Support. These differences make each platform better suited for specific use cases and organizational requirements.
⚠️ What This Comparison Covers
We'll analyze features, pricing, performance benchmarks, security compliance, integration capabilities, and real-world use cases to help you determine which platform best fits your organization's needs. All data is independently verified from official documentation and third-party review platforms.
Detailed Feature Comparison
Botpress
Tidio
CustomGPTRECOMMENDED
Data Ingestion & Knowledge Sources
Supported Formats: PDF, Word (DOC/DOCX), HTML, TXT, Markdown files via Studio UI and Files API
Website Crawling: Firecrawl integration for HTML-to-Markdown conversion with automatic sitemap detection
Real-Time Search: "Search The Web" feature using Bing API for queries when sitemaps unavailable
Cloud Integrations: Google Drive (OAuth sync with file upload/download triggers), Notion (database queries, page management)
Missing Integrations: No native Dropbox or Salesforce document ingestion
YouTube Limitation: No transcript ingestion support - requires manual transcription and text upload (Apify workaround exists but manual)
Automatic Retraining: Website sources sync regularly, file uploads managed dynamically through Files API
File Management: Replacing files automatically removes old content and indexes new content without downtime
Website URL crawling: Primary method scanning up to 500 URLs (expandable on Plus plans) with automatic Q&A pair extraction from web content
PDF uploads: Direct file upload support for PDF documents
CSV imports: Maximum 500 entries per file, 10,000 total Q&A limit across all sources
Manual Q&A creation: Admin panel configuration for custom question-answer pairs
Zendesk Help Center: Article import via API (closest to external knowledge integration available)
Automatic weekly re-sync: Website source updates available only on Plus/Premium plans
Continuous Q&A suggestions: System suggests new pairs from unanswered questions and historical conversations requiring manual review before activation
CRITICAL LIMITATION: No NO Word document (DOCX) support, No NO TXT files, No NO Excel files, No NO YouTube transcript processing, No NO audio/video file support, No NO code file ingestion
CRITICAL LIMITATION: No NO native cloud storage integrations - Google Drive, Dropbox, Notion connect via Zapier for workflows only (NOT as knowledge sources)
CRITICAL LIMITATION: No NO programmatic knowledge upload API - all data ingestion requires UI-based management, blocking automation workflows
Scaling constraint: 10,000 Q&A entry limit caps knowledge base size vs unlimited in RAG platforms
Per-conversation billing: Averaging $0.50 per AI conversation limits cost-effective scaling for high-volume use cases
Lets you ingest more than 1,400 file formats—PDF, DOCX, TXT, Markdown, HTML, and many more—via simple drag-and-drop or API.
Crawls entire sites through sitemaps and URLs, automatically indexing public help-desk articles, FAQs, and docs.
Turns multimedia into text on the fly: YouTube videos, podcasts, and other media are auto-transcribed with built-in OCR and speech-to-text.
View Transcription Guide
Connects to Google Drive, SharePoint, Notion, Confluence, HubSpot, and more through API connectors or Zapier.
See Zapier Connectors
Supports both manual uploads and auto-sync retraining, so your knowledge base always stays up to date.
Integrations & Channels
Native Channels: WhatsApp (Meta Business API), Slack (OAuth + Bot Framework), Microsoft Teams (Azure portal), Telegram (BotFather), Messenger, Instagram
SMS Support: Twilio and Vonage integrations for text messaging
Web Widget: JavaScript widget (recommended), DOM element mounting, full React component library for SPAs
Mobile Integration: React Native SDK (BpWidget, BpIncomingMessagesListener) for iOS/Android cross-platform support
Webhook Support: Unique webhook URL per bot with optional x-bp-secret header authentication and CORS configuration
Automation Platforms: Zapier integration (partially in beta - some features require manual activation)
Webhooks: Require Plus subscription ($749/month) for bidirectional data sync via Tray.io with real-time event notifications
Marketing tools: Google Analytics, Mailchimp, ActiveCampaign
CRITICAL GAPS: No NO native Slack integration (Zapier notifications only, not bidirectional chat), No NO Microsoft Teams integration, No NO Telegram native support (requires third-party Zapier/Make tools)
Embeds easily—a lightweight script or iframe drops the chat widget into any website or mobile app.
Offers ready-made hooks for Slack, Zendesk, Confluence, YouTube, Sharepoint, 100+ more.
Explore API Integrations
Connects with 5,000+ apps via Zapier and webhooks to automate your workflows.
Supports secure deployments with domain allowlisting and a ChatGPT Plugin for private use cases.
Hosted CustomGPT.ai offers hosted MCP Server with support for Claude Web, Claude Desktop, Cursor, ChatGPT, Windsurf, Trae, etc.
Read more here.
Conversational AI: Multi-turn dialogue with context retention across conversation sessions
Multi-Lingual: 100+ languages supported via Translator Agent with automatic translation
Knowledge Base Integration: RAG-powered answers grounded in uploaded documents and websites
Policy Agent: Customizable guardrails filtering outputs against defined policies for brand safety
Knowledge Agent: Structured retrieval before generation to reduce hallucinations
HITL Agent: Human-in-the-loop takeover when bot cannot answer (requires Team plan $495/month)
Personality Agent: Rewrites all bot messages to match defined persona (friendly, professional, casual, custom)
Autonomous Nodes: LLM decides which actions to execute based on conversation context
Performance Claims: "Zero hallucinations in 100,000 conversations" for health coaching client, 65% ticket deflection (no RAGAS scores or latency benchmarks published)
Lyro AI (Claude 3): 79-87% success rates (up from 50-70% pre-Claude 3 upgrade) with strict knowledge base boundaries preventing hallucinations
Lyro Guidance (beta): Tone customization (Neutral/Friendly/Formal), emoji toggles, source link display, custom escalation rules, communication style instructions
Human handoff: Transfer to unassigned queue, keep conversation with rephrasing, or create ticket with email follow-up - preserves full chat history and context
Smart Insights: AI-generated recommendations for improving metrics based on conversation analysis
Live visitor tracking: Real-time monitoring with typing preview and conversation takeover capabilities
45+ language support: Automatic browser-based detection with native multilingual processing (no internal English translation layer)
LIMITATION: No NO anti-hallucination controls beyond knowledge base boundaries - responses cannot be traced to source documents with citations (vs RAG platforms)
LIMITATION: No NO retrieval parameter configuration - users cannot adjust similarity thresholds, implement hybrid search, or configure confidence scoring
Custom AI Agents: Build autonomous agents powered by GPT-4 and Claude that can perform tasks independently and make real-time decisions based on business knowledge
Decision-Support Capabilities: AI agents analyze proprietary data to provide insights, recommendations, and actionable responses specific to your business domain
Multi-Agent Systems: Deploy multiple specialized AI agents that can collaborate and optimize workflows in areas like customer support, sales, and internal knowledge management
Memory & Context Management: Agents maintain conversation history and persistent context for coherent multi-turn interactions
View Agent Documentation
Tool Integration: Agents can trigger actions, integrate with external APIs via webhooks, and connect to 5,000+ apps through Zapier for automated workflows
Hyper-Accurate Responses: Leverages advanced RAG technology and retrieval mechanisms to deliver context-aware, citation-backed responses grounded in your knowledge base
Continuous Learning: Agents improve over time through automatic re-indexing of knowledge sources and integration of new data without manual retraining
Customization & Branding
Webchat Customization: Full CSS override via external stylesheet URL, custom colors/fonts/button styles/chat bubbles
Branding Control: Custom bot name and avatar, proactive greeting messages via JavaScript, configurable placement and sizing
White-Labeling: Remove "Powered by Botpress" watermark (requires Plus plan $89/month minimum)
Personality Configuration: Personality Agent defines bot persona with variable expressions for dynamic context
Persona Disable: Can be disabled at node level for specific interactions requiring different tone
Backend Branding: Admin dashboard remains Botpress-branded (no full white-label backend)
Multi-Tenant Limitation: No agency dashboard for managing multiple client bots under one interface
Real-Time Updates: Knowledge sources update via Files API without bot republishing for Table-based sources
Versioning Gap: No native versioning system - file replacement is manual with external version control required for rollback
UI customization: Visual live editor with theme presets, color pickers supporting custom hex codes, logo uploads, position controls (left/right), operating hours display automatically showing availability status
Branding control: Light/dark mode built-in theme switching with automatic user preference detection, custom CSS via JavaScript SDK for advanced styling beyond presets
White-labeling: $20/month addon on Growth tier OR included with Plus ($749+/month); not available on Free/Starter plans; custom branded agent avatars and logos require Plus plans minimum
Custom domain: Not explicitly documented in public materials; likely requires Plus or Premium plan with custom deployment infrastructure (specifics require sales engagement)
Design flexibility: Separate mobile widget settings with device-specific hiding options, mobile responsiveness with mobile-specific configuration separate from web widget
Mobile customization: Responsive widget adapts to mobile devices; mobile-specific branding controls inherit desktop configuration; mobile app functionality limitations noted in user reviews
Domain restrictions: Control which websites can embed widget through trusted domains configuration for security
Role-based access: Admin, Moderator, and Agent roles with configurable permissions on Growth+ plans; agent groups for departmental routing enabling organizational structure
Fully white-labels the widget—colors, logos, icons, CSS, everything can match your brand.
White-label Options
Provides a no-code dashboard to set welcome messages, bot names, and visual themes.
Lets you shape the AI’s persona and tone using pre-prompts and system instructions.
Uses domain allowlisting to ensure the chatbot appears only on approved sites.
In-Studio Presets: Two options - "Best Model" and "Fast Model" for quick selection
Alternative LLMs: Claude, Gemini, DeepSeek, LLaMA accessible via custom integrations or Execute Code cards with external API calls
No Automatic Routing: Deliberately avoided for "concerns about unpredictability and latency" - users manually select models per task
BYOK Limitation: Not natively supported - workaround involves storing API keys in Configuration Variables and Axios calls through Execute Code cards
AI Spend Pricing: Charged at-cost with no Botpress markup on OpenAI tokens
LLMz Engine: Proprietary inference layer with claimed improvements - better tool calling, token efficiency, TypeScript type definitions, V8 isolate execution
No Fine-Tuning: RAG recommended as primary approach, supplemented by "learnings" system providing relevant examples at prompt-time
CRITICAL LIMITATION: No Claude 3 LLM ONLY - NO model selection or routing available
Proprietary implementation: Tidio uses Claude 3 combined with proprietary control mechanisms (not publicly documented architecture)
Fixed processing: Cannot switch between GPT-3.5, GPT-4, Gemini, Llama, or custom models based on query complexity or cost optimization
NO BYOLLM: No No bring-your-own-model capabilities for enterprise customization or fine-tuning
Response personalization: Limited to Lyro Guidance instructions (tone, emoji, escalation rules) rather than direct prompt engineering
Competitive gap: Eliminates LLM flexibility entirely vs RAG platforms offering multi-provider model selection (rated 3/10 for model flexibility - major architectural limitation)
Taps into top models—OpenAI’s GPT-5.1 series, GPT-4 series, and even Anthropic’s Claude for enterprise needs (4.5 opus and sonnet, etc ).
Automatically balances cost and performance by picking the right model for each request.
Model Selection Details
Uses proprietary prompt engineering and retrieval tweaks to return high-quality, citation-backed answers.
Handles all model management behind the scenes—no extra API keys or fine-tuning steps for you.
Developer Experience ( A P I & S D Ks)
API Architecture: REST-only (no GraphQL) with base URL https://api.botpress.cloud/v1/
No Python SDK: Significant limitation for data science teams - other languages must use direct REST API access
Authentication: Three token types - Personal Access Token (PAT) for full access, Bot Access Key (BAK) for runtime, Integration Access Key (IAK) for integration-specific actions
Rate Limits: Exist but specifics not publicly documented - Studio limits lower than production bot limits (acknowledged by staff)
Documentation: Well-organized at botpress.com/docs with API references, video tutorials, "Ask AI" feature
Training Resources: Botpress Academy offers free courses
Three API tiers: Widget SDK (tidioChatAPI - free), OpenAPI REST (Plus $749/month), Webhooks (Plus $749/month)
Widget SDK (free): Controls widget open/close, user identification, event tracking via JavaScript tidioChatAPI interface
OpenAPI (REST): Manages contacts, tickets, conversations, operators with 10-120 requests/minute based on plan (Starter/Growth: 10/min, Plus: 60/min, Premium: 120/min)
Webhooks (Plus+): Real-time event notifications for conversations, tickets, customer satisfaction with 10-second response timeouts
Mobile SDKs: iOS and Android with full Lyro AI support and 15-30 minute implementation time, customizable UI styling within apps
Documentation: developers.tidio.com (beta status) with code snippets and interactive testing but limited depth for advanced use cases
CRITICAL LIMITATION: No NO official SDKs for any programming language (Python, JavaScript, Node.js) - requires direct HTTP calls to REST API
CRITICAL LIMITATION: No NO programmatic knowledge management endpoints - cannot upload documents, manage Q&A pairs, or configure knowledge base via API
CRITICAL LIMITATION: No NO Lyro AI querying API - cannot trigger AI responses or access retrieval endpoints programmatically
CRITICAL LIMITATION: No NO RAG-specific APIs for semantic search, embedding management, chunking configuration, or retrieval parameters
Support gap: Tidio explicitly states 'cannot provide direct assistance with API implementations' - developer support severely limited
Ships a well-documented REST API for creating agents, managing projects, ingesting data, and querying chat.
API Documentation
Performance Claims: "Zero hallucinations in 100,000 conversations" (one health coaching client), 65% ticket deflection
Benchmark Gap: No published RAGAS scores, latency measurements, or third-party validation
Scale Validation: 750,000+ active bots and 1 billion+ messages processed provide real-world proof of production reliability
LLMz Optimizations: Proprietary engine claims improved tool calling and token efficiency over standard OpenAI implementations
Response time: Real-time chat delivery optimized for sub-second messaging; exact latency benchmarks not publicly disclosed but consistently praised for responsiveness in G2 reviews (4.7/5, 1,600+ reviews)
Accuracy metrics: 79-87% Lyro AI success rate after Claude 3 upgrade (up from 50-70% pre-upgrade); customer case studies report 89-90% automation rates for well-configured implementations (Pizza Hut, Decathlon, Casio)
Context retrieval: Q&A extraction from URLs/PDFs/CSVs with automatic knowledge base building; strict knowledge base boundaries prevent hallucinations; no configurable similarity thresholds or hybrid search strategies exposed
Scalability: 300,000+ businesses served globally demonstrating SMB/e-commerce market fit; infrastructure supports high-volume deployments but per-conversation pricing model ($0.50/Lyro chat) constrains cost scaling vs unlimited usage platforms
Reliability: SLA guarantees on Premium tier ($2,999+/month) with 50% resolution guarantee and uptime commitments; platform stability consistently praised in reviews with "reliable" as common theme
Benchmarks: No published performance benchmarks comparing retrieval speed, accuracy, or latency against competitors; Claude 3 upgrade validation through customer case studies (89-90% automation rates)
Quality indicators: G2 rating 4.7/5 (1,600+ reviews, 68% five-star ratings); users praise ease of use, Shopify integration, visual Flow Builder, but note analytics depth limitations and per-conversation pricing at scale
Delivers sub-second replies with an optimized pipeline—efficient vector search, smart chunking, and caching.
Independent tests rate median answer accuracy at 5/5—outpacing many alternatives.
Benchmark Results
Always cites sources so users can verify facts on the spot.
Maintains speed and accuracy even for massive knowledge bases with tens of millions of words.
Customization & Flexibility
Real-Time Knowledge Updates: Files API enables adding/removing content anytime without bot downtime
Website Sync: Automatic crawling and re-indexing of connected websites on regular schedules
Personality Customization: Personality Agent defines consistent tone (friendly, professional, casual) with variable expressions
Node-Level Control: Disable Personality Agent for specific interactions requiring different behavior
Policy Agent Configuration: Define custom guardrails filtering outputs for brand safety and compliance
Execute Code Cards: Full TypeScript code execution within bot flows for unlimited custom logic
Autonomous Node Behavior: LLM-driven decision-making for which actions to execute in conversation
Versioning Limitation: No native rollback system - requires external version control and manual file replacement
Tables Feature: Structured data management for dynamic content and business logic integration
N/A
N/A
Pricing & Scalability
Pay-as-you-go: $0/month + AI Spend, 500 messages, 100MB vector storage, 1 bot, 1 collaborator, $5 AI credit included
Plus Plan: $89/month + AI Spend, 5,000 messages, 1GB vector storage, white-label, HITL, live chat support
Team Plan: $495/month + AI Spend, 50,000 messages, 2GB vector storage, RBAC, collaboration, 3 bots, custom analytics
Plus: $749/month - Custom billable (2,000+ conversations), up to 5,000 Lyro conversations, API access, webhooks, white-labeling, Customer Success Manager
Premium: $2,999+/month - Unlimited billable conversations, up to 10,000 Lyro conversations, 50% resolution guarantee, SLAs, unlimited operators
Per-conversation billing: Lyro AI costs approximately $0.50 per conversation (1 conversation = 1 customer interaction with AI reply, auto-closes after 15 minutes inactivity)
10-operator cap: Note: All self-serve plans (Free through Plus) limited to 10 operators - unlimited seats require Premium tier ($2,999+/month)
API access locked: Note: OpenAPI and Webhooks require Plus plan minimum ($749/month) - unavailable on Free/Starter/Growth tiers
White-labeling cost: Note: $20/month addon on Growth tier OR included with Plus ($749+/month)
Annual savings: ~20% discount when paying annually vs monthly billing
Cost scaling concern: Per-conversation model at $0.50/Lyro chat escalates costs at high volume vs unlimited usage in RAG platforms
Runs on straightforward subscriptions: Standard (~$99/mo), Premium (~$449/mo), and customizable Enterprise plans.
Gives generous limits—Standard covers up to 60 million words per bot, Premium up to 300 million—all at flat monthly rates.
View Pricing
Handles scaling for you: the managed cloud infra auto-scales with demand, keeping things fast and available.
Security & Privacy
SOC 2 Type 2: Certification in progress but not yet completed - critical gap for enterprise compliance
GDPR: Compliance claimed but no EU data residency available (all data processed/stored in US)
HIPAA: Not compliant - blocks healthcare use cases requiring protected health information
ISO 27001: Not certified
Data Residency: All data processed and stored in United States only - EU hosting "on roadmap" but not available
SSO Support: OAuth2 with Google, GitHub, Azure (Enterprise plan)
RBAC: Role-based access control available on Team tier ($495/month) and above
SCIM: User provisioning available on Enterprise plan only
Audit Logs: Enterprise plan includes comprehensive activity logging
Data Retention: Automatic deletion of personal log data, API endpoints for GDPR "right to be forgotten"
Training Privacy: Conversation data not used to train Botpress or third-party models
SOC 2 Type II: Achieved October 2025 through A-LIGN audit covering Security, Availability, and Confidentiality trust criteria
GDPR Compliant: May 2018 certification with designated Data Protection Officer and full subject rights support (access, rectification, erasure, portability)
AWS infrastructure: All customer data resides on AWS in EEA member countries for European data sovereignty
Encryption: TLS 1.2+ with 256-bit SSL for transit, AES-256 for data at rest, irreversible password hashing (no plaintext storage)
Two-factor authentication: TOTP-based 2FA available on all plans for account security
Role-based access control: Admin, Moderator, and Agent roles with configurable permissions on Growth+ plans
SSO: Single sign-on on Enterprise plans for centralized identity management
30-day audit logs: Available on Business plan for compliance tracking and security monitoring
AI data privacy: Lyro conversations NOT used for training public AI models - Anthropic's Claude processes in-session only without persistent data storage
LIMITATION: No NO HIPAA certification - SOC 2 Type II + GDPR only (Tidio indicates working toward healthcare compliance but no timeline)
Protects data in transit with SSL/TLS and at rest with 256-bit AES encryption.
Holds SOC 2 Type II certification and complies with GDPR, so your data stays isolated and private.
Security Certifications
Offers fine-grained access controls—RBAC, two-factor auth, and SSO integration—so only the right people get in.
Agent-level performance: Individual response times, handled conversation counts, workload distribution for team optimization
Real-time monitoring: Live visitor lists, typing preview, conversation takeover capabilities for immediate intervention
Lyro-specific analytics: Resolution rates, unanswered questions tracking, knowledge base gap identification for continuous improvement
Smart Insights: AI-generated recommendations for metric improvement based on conversation pattern analysis
Scheduled reports: Daily/weekly/monthly delivery via email with CSV export for custom analysis in external tools
LIMITATION: Note: Analytics depth falls short of enterprise expectations - users report 'helpful but not as detailed as enterprise tools' with limited funnel and flow-level analytics
LIMITATION: No NO AI performance metrics - no retrieval accuracy dashboards, semantic search performance tracking, hallucination rate monitoring (focuses on operational metrics)
Comes with a real-time analytics dashboard tracking query volumes, token usage, and indexing status.
Lets you export logs and metrics via API to plug into third-party monitoring or BI tools.
Analytics API
Provides detailed insights for troubleshooting and ongoing optimization.
Support & Ecosystem
Free Plan Support: Community only - Discord (31,000+ members), documentation, forums
Plus Plan Support: Live chat with Botpress engineers ($89/month)
Team Plan Support: Advanced support + solution engineering ($495/month)
Enterprise Support: Named support manager, SLA-backed response times (~$2,000+/month)
Discord Community: 31,000+ highly active members with daily discussions, feature requests, troubleshooting
Community Reputation: Users praise as "hands down the best Discord experience I have had"
Enterprise SLA: 99.8% uptime guarantee with service credits (5-25% depending on severity)
Response Time SLAs: 2 business days (standard Level 1) to 2 hours (premium Level 1)
Service Credit Cap: Maximum monthly credit 50% of charges
Excused Downtime: Includes OpenAI unavailability (notable caveat for external dependency)
Training Resources: Botpress Academy with free courses, video tutorials, documentation at botpress.com/docs
Support Limitation: Non-Enterprise users lack formal ticketing system, may wait for engineers on complex issues
Live chat support: Available with faster response times on higher tiers (24/7 on Plus/Premium)
Email support: All plans with tier-based priority levels
Customer Success Manager: Dedicated CSM on Plus ($749/month) for onboarding and optimization guidance
SLA guarantees: Premium tier ($2,999+/month) with 50% resolution guarantee and uptime commitments
Knowledge base: Self-service articles and video tutorials for common setup and troubleshooting scenarios
User satisfaction: 4.7/5 G2 rating (1,600+ reviews) with support quality consistently praised
LIMITATION: No NO public community forums or user groups for peer support and knowledge sharing
LIMITATION: No NO phone support available on any tier (chat and email only)
Developer support gap: Tidio explicitly states 'cannot provide direct assistance with API implementations' - technical support severely limited for custom integrations
Supplies rich docs, tutorials, cookbooks, and FAQs to get you started fast.
Developer Docs
Offers quick email and in-app chat support—Premium and Enterprise plans add dedicated managers and faster SLAs.
Enterprise Solutions
Benefits from an active user community plus integrations through Zapier and GitHub resources.
No- Code Interface & Usability
Visual Flow Builder: Node-based canvas with drag-and-drop conversation design
Autonomous Nodes: LLM decides action execution without manual flow definition
Knowledge Base UI: Drag-and-drop file upload (PDFs, documents), URL ingestion with automatic crawling, text input for manual content
Tables Feature: Visual structured data management without code
Visual Indexing: Available on Plus plan and above for knowledge base content organization
Pre-Built Templates: Recipe Bot, Recruitment Bot, Customer Support, Cinema Booking, AI Dungeon Master (~8 official templates + community contributions)
Template Customization: Predefined flows, knowledge bases, responses with full customization after import
Collaboration: Collaborator limits - 1 (free), 2 (Plus), 3 (Team), custom (Enterprise). Real-time simultaneous editing on Team plans
RBAC Requirement: Role-based access control requires Team plan ($495/month) - expensive for small teams
Code Extensibility: Execute Code cards allow TypeScript for advanced customization without leaving visual interface
Visual builder: Drag-and-drop Flow Builder for conversation automation with NLP intent recognition; no programming knowledge required (253 G2 'Ease of Use' mentions)
Setup complexity: 2-minute JavaScript snippet installation for website embedding; consistently praised in reviews for "easy setup" (161 G2 mentions) and rapid deployment
Learning curve: G2 rating 4.7/5 (1,600+ reviews) with "intuitive" interface for non-technical users; designed for business teams without developer resources vs API-centric platforms
Pre-built templates: 40+ pre-built templates for sales, lead generation, support scenarios reducing time-to-deployment; templates include common conversation flows and automation patterns
No-code workflows: Testing simulator validates flows before publishing with built-in emulation preventing production errors; export/import functionality for sharing flows between accounts or backup configurations
User experience: Lyro knowledge setup through simple URL or file upload with AI extracting Q&A pairs automatically - no technical skills required for configuration; HTTP request support (GET, POST, PATCH, PUT, DELETE) within chatbot automation supporting JSON, Text, GraphQL formats with multiple authentication methods
Competitive advantage: SMBs and non-technical teams deploy chatbots in minutes vs hours/days in API-centric platforms (9.5/10 rated differentiator for ease of use)
Offers a wizard-style web dashboard so non-devs can upload content, brand the widget, and monitor performance.
Supports drag-and-drop uploads, visual theme editing, and in-browser chatbot testing.
User Experience Review
Uses role-based access so business users and devs can collaborate smoothly.
R A G Capabilities
Platform Claim: "Most advanced RAG system in the market" - no independent benchmarks to validate
Standard RAG Pipeline: Document upload → format standardization → semantic chunking → embedding → vector storage → retrieval → generation
Semantic Chunking: Breaks documents into meaningful sections by topic rather than fixed character counts
Search API: contextDepth parameter for prepending/appending surrounding context to matching passages
Tag-Based Filtering: Scoped searches limited to specific knowledge subsets (max 50 results)
Client Results: Zero hallucinations in 100,000 conversations (health coaching client), 65% ticket deflection
Benchmark Gap: No RAGAS scores, latency measurements, or third-party validation published
Learnings System: Dynamically provides relevant examples at prompt-time to improve responses
Vector Storage: Purpose-built vector database with plan-based scaling (100MB to custom Enterprise)
CRITICAL ARCHITECTURAL GAP: NOT a RAG-as-a-Service platform: Lacks vector databases, embedding controls, and configurable retrieval pipelines found in true RAG systems
Q&A extraction system: Automatic Q&A pair generation from URLs/PDFs/CSVs through opaque internal processing - methodology not publicly documented
Knowledge base boundaries: Strict knowledge base boundaries prevent hallucinations - Lyro answers only from provided sources and automatically escalates when uncertain
NO chunking parameters exposed: Chunk size, overlap strategy, and chunking methodology not accessible for optimization or tuning
NO embedding model selection: Cannot choose between OpenAI, Cohere, custom embedding models, or configure embedding dimensions
NO similarity threshold controls: Cannot configure cosine similarity thresholds, retrieval scoring, confidence levels, or top-k results
NO hybrid search: No combination of keyword (BM25) and semantic search strategies or configurable weighting between approaches
NO anti-hallucination mechanisms: No citation attribution, source verification, or granular confidence scoring - responses cannot be traced to specific source documents
NO retrieval APIs: No programmatic access to semantic search, embedding management, or retrieval endpoints - knowledge management UI-only
Competitive positioning: Customer service automation platform with AI assistance, NOT autonomous knowledge retrieval system - fundamentally different architecture from RAG platforms (rated 2/10 as RAG platform)
Core architecture: GPT-4 combined with Retrieval-Augmented Generation (RAG) technology, outperforming OpenAI in RAG benchmarks
RAG Performance
Anti-hallucination technology: Advanced mechanisms reduce hallucinations and ensure responses are grounded in provided content
Benchmark Details
Automatic citations: Each response includes clickable citations pointing to original source documents for transparency and verification
Optimized pipeline: Efficient vector search, smart chunking, and caching for sub-second reply times
Scalability: Maintains speed and accuracy for massive knowledge bases with tens of millions of words
Context-aware conversations: Multi-turn conversations with persistent history and comprehensive conversation management
Source verification: Always cites sources so users can verify facts on the spot
Omnichannel Deployment
Messaging Platforms: WhatsApp (Meta Business API), Slack (OAuth + Bot Framework), Microsoft Teams (Azure portal registration)
Social Media: Telegram (BotFather setup - easy), Messenger, Instagram (Meta integration - medium complexity)
SMS Support: Twilio and Vonage integrations for text messaging channels
Web Deployment: JavaScript widget (recommended), DOM element mounting, React component library for SPAs
Mobile Apps: React Native SDK (BpWidget, BpIncomingMessagesListener) for iOS/Android cross-platform integration
Webhook Architecture: Unique webhook URL per bot with optional x-bp-secret header authentication
CORS Configuration: Customizable for web embedding and API access
Deployment Complexity: Ranges from easy (Telegram) to complex (Microsoft Teams Azure setup, WhatsApp Meta Business)
Hub Marketplace: 100+ integrations for extended channel and platform support
N/A
N/A
Visual Bot Building
Node-Based Canvas: Drag-and-drop conversation flow design with visual connections between nodes
Action Cards: Pre-built components for Text responses, Capture Information (forms), Execute Code (TypeScript), AI Tasks, Knowledge Base queries
Integration Actions: Direct connections to CRM (Salesforce, HubSpot), support (Zendesk), data sources
Autonomous Nodes: LLM-driven decision making for dynamic conversation paths without manual flow definition
Code Extensibility: Execute Code cards allow full TypeScript programming within visual flows
Knowledge Base Management: Visual drag-and-drop file upload, URL ingestion, text input, Tables for structured data
Template Library: ~8 official pre-built bots (Recipe, Recruitment, Support, Cinema, AI Dungeon Master) + community contributions
Real-Time Testing: Test conversations directly in Studio before deployment
Version Control: No native system - requires external Git integration and manual management
N/A
N/A
R A G-as-a- Service Assessment
Platform Type: CONVERSATIONAL AI PLATFORM WITH RAG (not pure RAG service)
Core Architecture: Full bot builder with integrated RAG capabilities (semantic chunking, vector storage, retrieval)
Service Model: Cloud SaaS with visual development environment and omnichannel deployment
RAG Implementation: Standard pipeline with semantic chunking, Policy Agent guardrails, Knowledge Agent retrieval
LLM Integration: Native OpenAI support only - alternatives require custom workarounds
Citation Support: Knowledge Agent provides source references but specificity level not documented
Enterprise Readiness: SOC 2 in progress (not certified), no EU data residency, not HIPAA compliant
RAG Focus: RAG is one feature within comprehensive conversational AI platform, not standalone RAG API
Platform classification: CUSTOMER SERVICE AUTOMATION PLATFORM with AI assistance, NOT a RAG-as-a-Service platform
Architecture philosophy: Designed for no-code chatbot building and agent productivity enhancement, not autonomous knowledge retrieval
Target audience: SMBs and e-commerce businesses needing easy chatbot deployment vs developers requiring programmatic RAG control
Missing RAG foundations: NO vector database, NO embedding controls, NO LLM model selection, NO anti-hallucination mechanisms, NO retrieval configuration APIs
Knowledge source gap: Limited to URLs, PDFs, CSVs (max 10,000 Q&A entries) vs 1,400+ formats and unlimited scaling in RAG platforms
API focus: Chat operations (contacts, tickets, conversations) vs RAG operations (semantic search, retrieval, embeddings, chunking)
Use case fit: Excellent for SMB customer service automation and e-commerce support, inappropriate for enterprise-scale document retrieval requiring accuracy controls
Competitive positioning: Different category from CustomGPT - customer service automation vs RAG-as-a-Service (rated 2/10 as RAG platform - fundamentally different architecture)
Core Architecture: Serverless RAG infrastructure with automatic embedding generation, vector search optimization, and LLM orchestration fully managed behind API endpoints
API-First Design: Comprehensive REST API with well-documented endpoints for creating agents, managing projects, ingesting data (1,400+ formats), and querying chat
API Documentation
Developer Experience: Open-source Python SDK (customgpt-client), Postman collections, OpenAI API endpoint compatibility, and extensive cookbooks for rapid integration
No-Code Alternative: Wizard-style web dashboard enables non-developers to upload content, brand widgets, and deploy chatbots without touching code
Hybrid Target Market: Serves both developer teams wanting robust APIs AND business users seeking no-code RAG deployment - unique positioning vs pure API platforms (Cohere) or pure no-code tools (Jotform)
RAG Technology Leadership: Industry-leading answer accuracy (median 5/5 benchmarked), 1,400+ file format support with auto-transcription, proprietary anti-hallucination mechanisms, and citation-backed responses
Benchmark Details
Deployment Flexibility: Cloud-hosted SaaS with auto-scaling, API integrations, embedded chat widgets, ChatGPT Plugin support, and hosted MCP Server for Claude/Cursor/ChatGPT
Enterprise Readiness: SOC 2 Type II + GDPR compliance, full white-labeling, domain allowlisting, RBAC with 2FA/SSO, and flat-rate pricing without per-query charges
Use Case Fit: Ideal for organizations needing both rapid no-code deployment AND robust API capabilities, teams handling diverse content types (1,400+ formats, multimedia transcription), and businesses requiring production-ready RAG without building ML infrastructure from scratch
Competitive Positioning: Bridges the gap between developer-first platforms (Cohere, Deepset) requiring heavy coding and no-code chatbot builders (Jotform, Kommunicate) lacking API depth - offers best of both worlds
Competitive Positioning
Primary Advantage: Visual bot building with code extensibility - accessible to non-developers, powerful for developers
Scale Validation: 750,000+ active bots and 1 billion+ messages processed prove production reliability at massive scale
Omnichannel Strength: Comprehensive native support for WhatsApp, Slack, Teams, Telegram, Messenger, SMS, web, mobile
Community Power: 31,000+ Discord members provide peer support, troubleshooting, best practices, feature validation
Primary Challenge: SOC 2 not certified, no EU data residency - critical gaps for enterprise buyers with compliance needs
Security Gap: Not HIPAA compliant, no ISO 27001 - blocks regulated industry adoption (healthcare, finance)
Cost Trade-Off: Free tier available but AI Spend unpredictability + feature paywalls (RBAC at $495/month) add complexity
Market Position: Conversational AI platform competing with Dialogflow, Rasa, Microsoft Bot Framework vs. pure RAG services
Use Case Fit: Ideal for teams needing visual bot building + multi-channel deployment vs. pure RAG API integrations
Platform vs. API: Full development environment with Studio, not lightweight RAG API - different target audience than CustomGPT
vs CustomGPT: Tidio excels in no-code ease of use and e-commerce integration; CustomGPT excels in RAG architecture and programmatic control
vs Intercom/LiveChat/Zendesk: Tidio competes in customer service automation with comparable features, lower pricing, stronger Shopify integration
vs Drift: Both focus on conversational automation - Tidio emphasizes SMB/e-commerce support, Drift emphasizes enterprise sales teams
vs RAG platforms (Vectara, Pinecone Assistant, Ragie): Fundamentally different architecture - Tidio not designed for autonomous retrieval, lacks RAG infrastructure
Market niche: No-code customer service automation for SMBs and e-commerce with exceptional ease of use (4.7/5 G2), NOT a RAG alternative for knowledge retrieval
Market position: Leading all-in-one RAG platform balancing enterprise-grade accuracy with developer-friendly APIs and no-code usability for rapid deployment
Target customers: Mid-market to enterprise organizations needing production-ready AI assistants, development teams wanting robust APIs without building RAG infrastructure, and businesses requiring 1,400+ file format support with auto-transcription (YouTube, podcasts)
Key competitors: OpenAI Assistants API, Botsonic, Chatbase.co, Azure AI, and custom RAG implementations using LangChain
Competitive advantages: Industry-leading answer accuracy (median 5/5 benchmarked), 1,400+ file format support with auto-transcription, SOC 2 Type II + GDPR compliance, full white-labeling included, OpenAI API endpoint compatibility, hosted MCP Server support (Claude, Cursor, ChatGPT), generous data limits (60M words Standard, 300M Premium), and flat monthly pricing without per-query charges
Pricing advantage: Transparent flat-rate pricing at $99/month (Standard) and $449/month (Premium) with generous included limits; no hidden costs for API access, branding removal, or basic features; best value for teams needing both no-code dashboard and developer APIs in one platform
Use case fit: Ideal for businesses needing both rapid no-code deployment and robust API capabilities, organizations handling diverse content types (1,400+ formats, multimedia transcription), teams requiring white-label chatbots with source citations for customer-facing or internal knowledge projects, and companies wanting all-in-one RAG without managing ML infrastructure
A I Models
Native OpenAI Support: GPT-4o, GPT-4o mini, GPT-4 Turbo with in-Studio presets ("Best Model" and "Fast Model" for quick selection)
Claude Models: Claude 4 Sonnet, Claude 3.5 Sonnet, Claude 3.7 Sonnet, Claude 4.5 Sonnet accessible via custom integrations or Execute Code cards
Google Gemini: Gemini Pro, Gemini 2.5 Flash available through external API calls in custom integrations
Open Source Options: LLaMA, DeepSeek accessible via Execute Code cards with external API integration
Model Access within Days: Platform provides access to latest LLMs within days of release for every chatbot built on Botpress
No Automatic Routing: Deliberately avoided for "concerns about unpredictability and latency" - users manually select models per task
LLMz Engine: Proprietary inference layer with claimed improvements - better tool calling, token efficiency, TypeScript type definitions, V8 isolate execution
AI Spend Pricing: Charged at-cost with no Botpress markup on OpenAI tokens; option to use Botpress-managed credits or BYOK (bring your own key)
No Fine-Tuning: RAG recommended as primary approach, supplemented by "learnings" system providing relevant examples at prompt-time
Fixed Claude 3 implementation: Lyro AI exclusively powered by Anthropic's Claude 3 with proprietary control mechanisms - no model selection available
Model selection rationale: Claude chosen for being "developed with the goal of becoming helpful, honest, and harmless" - explicit decision prioritizing safety over GPT alternatives
Success rate improvement: 79-87% automation rate after Claude 3 upgrade (up from 50-70% with pre-Claude 3 models) demonstrating significant performance gains
Customer automation rates: Case studies report 89-90% automation for well-configured implementations (Pizza Hut, Decathlon, Casio validation)
CRITICAL LIMITATION: NO model switching: Cannot switch between GPT-3.5, GPT-4, Gemini, Llama, or custom models based on query complexity or cost optimization needs
CRITICAL LIMITATION: NO BYOLLM: No bring-your-own-model capabilities for enterprise customization or fine-tuning on proprietary data
CRITICAL LIMITATION: NO automatic routing: No intelligent model routing, fallback strategies, or load balancing across different LLM providers
Response personalization limits: Customization restricted to Lyro Guidance instructions (tone, emoji, escalation rules) rather than direct prompt engineering or system prompts
Competitive gap: Eliminates LLM flexibility entirely vs RAG platforms offering multi-provider model selection (rated 3/10 for model flexibility - major architectural limitation)
Primary models: GPT-5.1 and 4 series from OpenAI, and Anthropic's Claude 4.5 (opus and sonnet) for enterprise needs
Automatic model selection: Balances cost and performance by automatically selecting the appropriate model for each request
Model Selection Details
Proprietary optimizations: Custom prompt engineering and retrieval enhancements for high-quality, citation-backed answers
Managed infrastructure: All model management handled behind the scenes - no API keys or fine-tuning required from users
Anti-hallucination technology: Advanced mechanisms ensure chatbot only answers based on provided content, improving trust and factual accuracy
Use Cases
Customer Support: Most popular use case with 98% of chats resolved without human intervention (Ruby Labs: 4 million support chats monthly)
Sales Automation: Majority of deployed bots part of sales process - appointment scheduling, lead nurturing, product suggestions, competitive comparisons, automated follow-ups
Sales Impact: Businesses report average 67% sales increase using chatbots, projected $112 billion in retail sales for 2024
Enterprise Internal Use: HR chatbots for vacation requests, IT chatbots for employee tech troubleshooting, repetitive high-volume task automation
Lead Generation: AI lead generation qualifies leads through conversational engagement, needs assessment, information gathering, automated follow-up
Cost Savings: One bank saved €530,000 by deploying chatbot, demonstrating measurable enterprise ROI
Multi-Channel Engagement: WhatsApp Business API, Slack, Microsoft Teams, Telegram, Messenger, Instagram, SMS (Twilio/Vonage) for comprehensive reach
Scale Validation: 750,000+ active bots, 1 billion+ messages processed provide real-world production reliability proof
SMB customer service automation: Perfect for small-to-medium businesses needing easy chatbot deployment for basic support queries (4.7/5 G2 rating, 1,600+ reviews)
E-commerce support: Deep Shopify/WooCommerce integration for order management, cart recovery, and product recommendations - 60,000+ WordPress installations demonstrate e-commerce fit
Multi-channel support: Unified inbox for website live chat, Facebook Messenger, Instagram DMs, WhatsApp Business API, email ticketing (omnichannel deployment)
No-code chatbot building: Visual Flow Builder with 40+ templates enables non-technical teams to deploy chatbots in minutes without developer resources
Lead generation and qualification: Capture visitor information, qualify leads through conversation flows, sync to CRM platforms (Salesforce, HubSpot, Pipedrive)
NOT ideal for: Enterprise-scale document retrieval requiring accuracy controls, RAG applications needing semantic search and embedding configuration, or knowledge-intensive use cases requiring citation validation
NOT ideal for: Organizations requiring programmatic knowledge management APIs, LLM model flexibility (GPT-4/Gemini switching), or advanced RAG features (hybrid search, reranking, query expansion)
NOT ideal for: High-volume automation (per-conversation pricing at $0.50/chat escalates costs vs unlimited usage platforms), teams needing more than 10 operators (Premium tier required at $2,999+/month)
Customer support automation: AI assistants handling common queries, reducing support ticket volume, providing 24/7 instant responses with source citations
Internal knowledge management: Employee self-service for HR policies, technical documentation, onboarding materials, company procedures across 1,400+ file formats
Sales enablement: Product information chatbots, lead qualification, customer education with white-labeled widgets on websites and apps
Documentation assistance: Technical docs, help centers, FAQs with automatic website crawling and sitemap indexing
Educational platforms: Course materials, research assistance, student support with multimedia content (YouTube transcriptions, podcasts)
Healthcare information: Patient education, medical knowledge bases (SOC 2 Type II compliant for sensitive data)
Data Retention: Automatic deletion of personal log data, API endpoints for GDPR "right to be forgotten" compliance
Training Privacy: Conversation data NOT used to train Botpress or third-party models
SOC 2 Type II certified: Achieved October 2025 through A-LIGN audit covering Security, Availability, and Confidentiality trust criteria - demonstrates enterprise-grade security controls
GDPR Compliant: May 2018 certification with designated Data Protection Officer and full subject rights support (access, rectification, erasure, portability, restriction)
AWS infrastructure: All customer data resides on AWS in EEA member countries for European data sovereignty and GDPR compliance
Encryption standards: TLS 1.2+ with 256-bit SSL for data in transit, AES-256 for data at rest, irreversible password hashing (no plaintext storage)
Two-factor authentication: TOTP-based 2FA available on all plans for account security hardening
Role-based access control: Admin, Moderator, and Agent roles with configurable permissions on Growth+ plans; agent groups for departmental routing
SSO: Single sign-on available on Enterprise plans for centralized identity management and authentication
30-day audit logs: Available on Business plan for compliance tracking, security monitoring, and incident investigation
AI data privacy: Lyro conversations NOT used for training public AI models - Anthropic's Claude processes in-session only without persistent data storage or model training
LIMITATION: NO HIPAA certification: SOC 2 Type II + GDPR only - Tidio indicates working toward healthcare compliance but no timeline or BAA availability
LIMITATION: Limited compliance scope: No ISO 27001, PCI DSS Level 1, or FedRAMP certifications limiting adoption in regulated industries beyond basic GDPR
Encryption: SSL/TLS for data in transit, 256-bit AES encryption for data at rest
SOC 2 Type II certification: Industry-leading security standards with regular third-party audits
Security Certifications
GDPR compliance: Full compliance with European data protection regulations, ensuring data privacy and user rights
Access controls: Role-based access control (RBAC), two-factor authentication (2FA), SSO integration for enterprise security
Data isolation: Customer data stays isolated and private - platform never trains on user data
Domain allowlisting: Ensures chatbot appears only on approved sites for security and brand protection
Secure deployments: ChatGPT Plugin support for private use cases with controlled access
Pricing & Plans
Pay-as-you-go (Free): $0/month + AI Spend, 500 messages, 100MB vector storage, 1 bot, 1 collaborator, $5 AI credit included
Plus Plan: $89/month + AI Spend, 5,000 messages, 1GB vector storage, white-label, HITL, live chat support
Team Plan: $495/month + AI Spend, 50,000 messages, 2GB vector storage, RBAC, collaboration, 3 bots, custom analytics
Growth: $59-$349/month - 250-2,000 billable conversations, Lyro separate addon, advanced analytics, Shopify actions, 10 operators, agent groups
Plus: $749/month - Custom billable (2,000+ conversations), up to 5,000 Lyro conversations, API access, webhooks, white-labeling, Customer Success Manager, 10 operators
Premium: $2,999+/month - Unlimited billable conversations, up to 10,000 Lyro conversations, 50% resolution guarantee, SLAs, unlimited operators, dedicated support
Lyro AI pricing: Approximately $0.50 per conversation (1 conversation = 1 customer interaction with AI reply, auto-closes after 15 minutes inactivity) - separate addon on Growth tier
10-operator cap NOTE: All self-serve plans (Free through Plus) limited to 10 operators - unlimited seats require Premium tier ($2,999+/month) blocking team scalability
API access locked: OpenAPI REST endpoints and Webhooks require Plus plan minimum ($749/month) - unavailable on Free/Starter/Growth tiers limiting integration options
White-labeling cost: $20/month addon on Growth tier OR included with Plus ($749+/month) - not available on Free/Starter plans
Annual savings: Approximately 20% discount when paying annually vs monthly billing across all tiers
Cost scaling concern: Per-conversation model at $0.50/Lyro chat escalates costs significantly at high volume vs unlimited usage in RAG platforms - $500/month for 1,000 AI conversations
Standard Plan: $99/month or $89/month annual - 10 custom chatbots, 5,000 items per chatbot, 60 million words per bot, basic helpdesk support, standard security
View Pricing
Premium Plan: $499/month or $449/month annual - 100 custom chatbots, 20,000 items per chatbot, 300 million words per bot, advanced support, enhanced security, additional customization
Enterprise Plan: Custom pricing - Comprehensive AI solutions, highest security and compliance, dedicated account managers, custom SSO, token authentication, priority support with faster SLAs
Enterprise Solutions
7-Day Free Trial: Full access to Standard features without charges - available to all users
Annual billing discount: Save 10% by paying upfront annually ($89/mo Standard, $449/mo Premium)
Flat monthly rates: No per-query charges, no hidden costs for API access or white-labeling (included in all plans)
Managed infrastructure: Auto-scaling cloud infrastructure included - no additional hosting or scaling fees
Support & Documentation
Free Plan Support: Community only - Discord (31,000+ members), documentation, forums - no direct support
Plus Plan Support: Live chat with Botpress engineers ($89/month) for direct technical assistance
Team Plan Support: Advanced support + solution engineering ($495/month) for complex implementations
Enterprise Support: Named support manager, SLA-backed response times (2 hours to 2 business days), ~$2,000+/month
Discord Community: 31,000+ highly active members with daily discussions, feature requests, troubleshooting - praised as "best Discord experience"
Documentation: Comprehensive docs at botpress.com/docs with API references, video tutorials, "Ask AI" feature for guided help
Botpress Academy: Free training courses covering bot development, best practices, advanced features
Response Time SLAs: 2 business days (standard Level 1) to 2 hours (premium Level 1) for Enterprise customers
Service Credits: 99.8% uptime SLA with credits for downtime, includes OpenAI unavailability (notable external dependency caveat)
Support Limitation: Non-Enterprise users lack formal ticketing system, may experience wait times for complex issues
Live chat support: Available on all plans with tier-based response times (24/7 on Plus/Premium vs business hours on lower tiers)
Email support: All plans with priority levels based on subscription tier - fastest response on Premium
Customer Success Manager: Dedicated CSM on Plus ($749/month) for onboarding guidance, optimization strategy, and ongoing consultation
SLA guarantees: Premium tier ($2,999+/month) with 50% resolution guarantee and uptime commitments for mission-critical deployments
Knowledge base: Self-service articles and video tutorials for common setup scenarios, troubleshooting guides, and feature configuration
User satisfaction: 4.7/5 G2 rating (1,600+ reviews) with support quality consistently praised; 68% five-star ratings demonstrate high satisfaction
LIMITATION: NO public community forums: No user community, Slack workspace, or Discord server for peer support and knowledge sharing among users
LIMITATION: NO phone support: No phone support available on any tier (chat and email only) limiting support options for urgent issues
Developer support gap: Tidio explicitly states 'cannot provide direct assistance with API implementations' - technical support severely limited for custom integrations requiring code
Documentation hub: Rich docs, tutorials, cookbooks, FAQs, API references for rapid onboarding
Developer Docs
Email and in-app support: Quick support via email and in-app chat for all users
Premium support: Premium and Enterprise plans include dedicated account managers and faster SLAs
Code samples: Cookbooks, step-by-step guides, and examples for every skill level
API Documentation
Active community: User community plus 5,000+ app integrations through Zapier ecosystem
Regular updates: Platform stays current with ongoing GPT and retrieval improvements automatically
Additional Considerations
High learning curve: Platform highly flexible but non-technical users struggle with advanced flow builder and developer-oriented features
Developer dependency: No quick copy-and-paste solution for real enterprise - company needs long-term employees ready to see it through with recommended 1-2 developers and 1-2 business-side employees per project
Performance under load: Live users report latency and webhook timeout issues under spiky high-concurrency loads - high-traffic teams should stress-test with projected peak traffic
Self-hosting complexity: For enterprise deployments with large numbers of bots or conversations self-hosting might be required shifting maintenance and scaling challenges to your team
Technical requirements: Configuring Docker, Kubernetes, databases, and certificates can become roadblock - requires skills in JavaScript, API integration, NLP, state management
DevOps investment needed: Teams should be prepared for additional DevOps investment for autoscaling, database sharding, and backup strategies
Unpredictable AI usage costs: Every message, retrieval, or workflow call consumes tokens making monthly bills swing dramatically depending on traffic and complexity
Hidden expenses: Third-party services like WhatsApp, SMS, voice integrations billed separately - advanced use cases often require engineering hours, enterprise deployments may require onboarding packages, compliance audits, or custom module builds costing thousands
Scaling costs: Growing from 5,000 to 20,000 MAUs means moving from $495/month to much higher custom enterprise price - multiple bots, custom integrations, or premium add-ons can push monthly spend well past initial plan quote
Resource-heavy features: Botpress LLM features can be resource-heavy requiring wise CPU/memory allocation planning
Commercial license threshold: Planning more than 150K interactions per month requires commercial license
Ongoing maintenance: Deployment is just start - bots must be continuously monitored, tested, and iterated to stay effective and aligned with evolving business goals
Platform Classification: CUSTOMER SERVICE AUTOMATION PLATFORM with AI assistance, NOT a RAG-as-a-Service platform - designed for no-code chatbot building and agent productivity
Target Audience Fit: SMBs and e-commerce businesses needing easy chatbot deployment without developer dependency vs enterprises requiring programmatic RAG control
Primary Strength: Exceptional ease of use (4.7/5 G2, 253 'Ease of Use' mentions) with Visual Flow Builder enabling non-technical teams to deploy chatbots in minutes vs hours/days in API-centric platforms
Claude 3 AI Performance: 79-87% success rates (up from 50-70% pre-Claude 3 upgrade) with customer case studies reporting 89-90% automation for well-configured implementations (Pizza Hut, Decathlon, Casio)
Multilingual Excellence: 45+ languages with native processing (no internal English translation layer) and automatic browser detection reduces accuracy loss vs translation-based competitors
Shopify Integration Depth: Order management, cart preview/recovery, product catalog access directly from chat interface - 60,000+ WordPress installations validate e-commerce market fit
CRITICAL LIMITATION - NOT a RAG Platform: Missing RAG foundations (NO vector database, NO embedding controls, NO LLM model selection, NO anti-hallucination mechanisms, NO retrieval configuration APIs)
CRITICAL LIMITATION - Knowledge Source Gap: Limited to URLs, PDFs, CSVs with 10,000 Q&A entry limit vs unlimited documents and 1,400+ formats in RAG platforms
CRITICAL LIMITATION - Fixed Claude 3 Model: NO model selection, routing, or BYOLLM capabilities - eliminates LLM flexibility entirely (rated 3/10 for model flexibility)
API Limitations: OpenAPI and Webhooks require Plus plan minimum ($749/month) - unavailable on Free/Starter/Growth tiers limiting integration options
Cost Scaling Concern: Per-conversation model at $0.50/Lyro chat escalates quickly at high volume (1,000 AI conversations = $500/month) vs unlimited usage platforms
10-Operator Cap: All self-serve plans limited to 10 operators until Premium tier ($2,999+/month) restricting team scalability for growing businesses
Use Case Mismatch: Excellent for SMB customer service automation and e-commerce support; inappropriate for enterprise-scale document retrieval requiring accuracy controls
Slashes engineering overhead with an all-in-one RAG platform—no in-house ML team required.
Gets you to value quickly: launch a functional AI assistant in minutes.
Stays current with ongoing GPT and retrieval improvements, so you’re always on the latest tech.
Balances top-tier accuracy with ease of use, perfect for customer-facing or internal knowledge projects.
Core Chatbot Features
Advanced AI capabilities: Extremely advanced AI with multiple sophisticated AI agents - automatic translation, conversation summarization, Vision Agent for image understanding
LLMz custom inference engine: Core of every Botpress agent with proprietary engine for enhanced performance
Conversational memory: Rich conversational memory maintaining context across long interactions, understanding complex multi-turn queries, and generating human-like responses
User memory across sessions: Agent remembers conversation history of specific users across different times - recalls user preferences, where they left off, and preferred tone of voice
Visual flow builder: Drag-and-drop interface for designing complex conversational flows without coding
Built-in AI features: Intent recognition, entity extraction, knowledge base integration, and AI agents
Custom data training: Train chatbot on custom data like website and documents
Multi-channel deployment: Create and launch chatbots on many channels including website, Facebook, WhatsApp, Slack, Instagram and more platforms
API integrations: Integrates with APIs, CRMs, databases, and other business applications
Automatic translation: Over 100 languages for global reach
AI Swarms/Teams (2025): Platform transformed into mature "AI workforce deployment and management center" with AI team collaboration capabilities
Live Database Connectors: Breakthrough feature allowing direct secure connection to SQL or NoSQL database in addition to traditional API connections
Open-source flexibility: Users have access to application source code and can contribute to development - skilled developers can push envelope to tailor to unique needs
Lyro AI (Claude 3): 79-87% success rates (up from 50-70% pre-Claude 3 upgrade) with strict knowledge base boundaries preventing hallucinations beyond provided sources
Lyro Guidance (beta): Tone customization (Neutral/Friendly/Formal), emoji toggles, source link display, custom escalation rules, communication style instructions for brand voice consistency
Human Handoff Logic: Transfer to unassigned queue, keep conversation with rephrasing, or create ticket with email follow-up - preserves full chat history and context for seamless transitions
Smart Insights: AI-generated recommendations for improving metrics based on conversation pattern analysis - identifies optimization opportunities automatically
Live Visitor Tracking: Real-time monitoring with typing preview and conversation takeover capabilities for immediate human intervention when needed
45+ Language Support: Automatic browser-based detection with native multilingual processing (no internal English translation layer reduces accuracy loss)
Visual Flow Builder: Drag-and-drop interface for conversation flows with intent detection nodes, entity extraction, event triggers, variable management, memory retention
NO Anti-Hallucination Controls: Responses cannot be traced to source documents with citations - no citation attribution, source verification, or granular confidence scoring vs RAG platforms
NO Retrieval Parameter Configuration: Users cannot adjust similarity thresholds, implement hybrid search, configure confidence scoring, or tune retrieval mechanisms
Reduces hallucinations by grounding replies in your data and adding source citations for transparency.
Benchmark Details
Handles multi-turn, context-aware chats with persistent history and solid conversation management.
Speaks 90+ languages, making global rollouts straightforward.
Includes extras like lead capture (email collection) and smooth handoff to a human when needed.
Knowledge Bases: Upload in variety of formats ranging from website or document to custom text file or Table
Knowledge Base scoping: Scope which Knowledge Bases Autonomous Node searches by organizing documents into folders limiting availability to certain workflows
Search field configuration: Configure search fields such as name, description, power, price to refine bot responses
Dynamic management: Programmatically manage Knowledge Base files with Botpress API to dynamically add, update, or remove content in real time keeping AI agent knowledge current
Behavior customization: Define specific behaviors in instructions to avoid unintended outputs - specify prices are final and include all discounts to prevent bot from fabricating discounts
Custom responses: Program custom response by adding Transition Card in Autonomous Node and handle transition however wanted with custom error messages
Bot templates: Pre-configured projects containing predefined conversational flows, Knowledge Bases, and responses serving as starting point - easily customized and extended to meet specific requirements with full developer control
Visual customization: Give bot name, store avatar URL for custom icon, provide general description, formulate placeholder text displayed before user enters first text
ChatGPT consultation: Customize bot behavior deciding when to consult ChatGPT based on knowledge base responses
Highly customizable workflows: Unlimited variables and open-source flexibility for advanced customization
Knowledge Base Building: URL crawling (500 URLs expandable on Plus), PDF uploads, CSV imports (max 500 entries/file, 10,000 total Q&A limit), manual Q&A creation, Zendesk Help Center article import
Automatic Weekly Re-Sync: Website source updates available on Plus/Premium plans ensuring knowledge stays current without manual refresh
Continuous Q&A Suggestions: System suggests new pairs from unanswered questions and historical conversations requiring manual review before activation
Behavior Customization: Lyro Guidance enables tone (Neutral/Friendly/Formal), emoji toggles, escalation rules, communication style instructions without coding requirements
Visual Flow Builder: No-code workflow creation with real-time testing simulator, one-click deployment, automatic versioning with rollback capabilities for rapid iteration
HTTP Request Support: GET, POST, PATCH, PUT, DELETE within chatbot automation supporting JSON, Text, GraphQL formats with multiple authentication methods
40+ Pre-Built Templates: Sales, lead generation, support scenarios reduce time-to-deployment with industry-specific conversation flows
Widget Customization: Visual live editor with theme presets, color pickers (custom hex), logo uploads, position controls (left/right), operating hours display
CRITICAL LIMITATION - Opaque Q&A Extraction: Knowledge processing methodology not publicly documented - no transparency into chunking strategies, embedding models, or retrieval mechanisms
CRITICAL LIMITATION - NO Programmatic Knowledge API: Cannot upload documents, manage Q&A pairs, or configure knowledge base via API - all data ingestion requires UI-based management
CRITICAL LIMITATION - 10,000 Q&A Entry Limit: Hard cap on knowledge base size vs unlimited in RAG platforms constrains large-scale deployments
Lets you add, remove, or tweak content on the fly—automatic re-indexing keeps everything current.
Shapes agent behavior through system prompts and sample Q&A, ensuring a consistent voice and focus.
Learn How to Update Sources
Supports multiple agents per account, so different teams can have their own bots.
Balances hands-on control with smart defaults—no deep ML expertise required to get tailored behavior.
Limitations & Considerations
Steep Learning Curve: Platform highly flexible but non-technical users struggle with advanced flow builder and developer-oriented features
Developer Dependency: Requires developer involvement making it less suitable for small businesses needing quick setup
Bug Disruptions: Various bugs may disrupt workflows and cause functionality problems requiring troubleshooting
Missing Features: White-labeling, global compliance, seamless live support require heavy effort or unavailable, slowing adoption
Data Visibility Gap: Cannot see user variables (name, email, custom fields) in chatbot conversations - limits analytics capabilities
Cost for SMBs: Enterprise-level security, compliance, dedicated support cost prohibitive for smaller teams ($495-$2,000+/month)
Resource Requirements: Self-hosted deployment requires IT resources for deployment and ongoing management
Complex Setup: Publishing on Facebook/Instagram technically complex, live chat only available on higher-priced plans
Limited Analytics: Standard plans offer limited analytical capabilities - advanced analytics require Team plan ($495/month)
LLM Provider Dependency: Reliance on third-party LLM providers (primarily OpenAI) impacts operational costs, scalability, and control
Complex Issue Handling: Chatbots may struggle with handling complex, nuanced customer issues requiring human judgment
Multi-Instance Challenges: Setting up multiple instances from one installation proven difficult for some enterprise users
Compliance Gaps: SOC 2 incomplete, no HIPAA, no ISO 27001, US-only data residency blocks regulated industries and EU enterprises
NOT a RAG platform: Customer service automation platform, NOT RAG-as-a-Service - lacks vector databases, embedding controls, configurable retrieval pipelines (rated 2/10 as RAG alternative)
Limited knowledge sources: Restricted to URLs, PDFs, CSVs with 10,000 Q&A entry limit vs unlimited documents and 1,400+ formats in RAG platforms
No programmatic knowledge API: Cannot upload documents, manage Q&A pairs, or configure knowledge base via API - all knowledge management requires UI interaction
No Lyro AI querying API: Cannot trigger AI responses or access retrieval endpoints programmatically - API limited to chat operations (contacts, tickets, conversations)
Fixed Claude 3 model: NO model selection, routing, or BYOLLM capabilities - eliminates LLM flexibility entirely (rated 3/10 for model flexibility)
Analytics depth limitations: Users report analytics "helpful but not as detailed as enterprise tools" with limited funnel and flow-level analytics vs specialized platforms
No AI performance metrics: No retrieval accuracy dashboards, semantic search performance tracking, hallucination rate monitoring, or confidence scoring visibility
Per-conversation pricing scaling: $0.50/Lyro chat costs escalate quickly at high volumes (1,000 AI conversations = $500/month) vs unlimited usage competitors
10-operator cap constraint: Self-serve plans limited to 10 operators until Premium tier ($2,999+/month) restricting team scalability for growing businesses
No native Slack/Teams integration: Only Zapier notifications available - no bidirectional chat or native bot deployment in workplace messaging platforms
Knowledge Base accuracy concerns: Opaque Q&A extraction methodology without retrieval parameter controls or hybrid search capabilities limiting accuracy vs specialized RAG platforms
Managed service approach: Less control over underlying RAG pipeline configuration compared to build-your-own solutions like LangChain
Vendor lock-in: Proprietary platform - migration to alternative RAG solutions requires rebuilding knowledge bases
Model selection: Limited to OpenAI (GPT-5.1 and 4 series) and Anthropic (Claude, opus and sonnet 4.5) - no support for other LLM providers (Cohere, AI21, open-source models)
Pricing at scale: Flat-rate pricing may become expensive for very high-volume use cases (millions of queries/month) compared to pay-per-use models
Customization limits: While highly configurable, some advanced RAG techniques (custom reranking, hybrid search strategies) may not be exposed
Language support: Supports 90+ languages but performance may vary for less common languages or specialized domains
Real-time data: Knowledge bases require re-indexing for updates - not ideal for real-time data requirements (stock prices, live inventory)
Enterprise features: Some advanced features (custom SSO, token authentication) only available on Enterprise plan with custom pricing
Shopify Deep Integration ( Core Differentiator)
N/A
Order management: View customer order history, track shipments, process refunds directly from chat interface without leaving conversation
Cart preview and recovery: See abandoned carts, send automated recovery messages, provide product recommendations based on browsing
Product catalog access: Search and display products from Shopify store within chat with images, pricing, and direct purchase links
Customer data sync: Automatic synchronization of customer profiles, purchase history, preferences for personalized support
Competitive positioning: Deep Shopify/WooCommerce capabilities vs RAG platforms' generic web integrations position Tidio strongly for e-commerce use cases
No-code automation: Drag-and-drop interface for conversation flow creation without programming knowledge (253 G2 'Ease of Use' mentions)
40+ pre-built templates: Sales, lead generation, support scenarios reduce time-to-deployment for common use cases
Testing simulator: Validate flows before publishing with built-in emulation preventing production errors
Export/import functionality: Share flows between accounts or backup configurations for versioning
HTTP request support: GET, POST, PATCH, PUT, DELETE within chatbot automation supporting JSON, Text, GraphQL formats with multiple authentication methods
Target audience advantage: Non-technical business users can deploy chatbots in minutes vs developer-required platforms (9/10 rated differentiator for SMBs)
User feedback: G2 reviews cite 'Easy Setup' (161 mentions) and 'intuitive' workflow design as primary strengths
N/A
Claude 3 A I Performance ( Differentiator)
N/A
Model selection rationale: Anthropic's Claude chosen for being "developed with the goal of becoming helpful, honest, and harmless" - explicit decision over GPT
Success rate improvement: Jumped from 50-70% to 79-87% after Claude 3 upgrade demonstrating significant model advancement
Customer automation rates: Case studies report 89-90% automation for well-configured implementations (Pizza Hut, Decathlon, Casio use cases)
Hallucination prevention: Strict knowledge base boundaries - Lyro answers only from provided sources and automatically escalates when uncertain
Privacy advantage: Anthropic processes conversations in-session only without saving data unnecessarily vs competitors using data for training
LIMITATION: No Fixed Claude 3 implementation - NO model switching, NO automatic routing, NO GPT/Gemini/custom model options (7/10 rated as limitation vs flexible RAG platforms)
N/A
Widget Customization & White- Labeling
N/A
Visual customization: Live editor with theme presets, color pickers (custom hex supported), logo uploads, position controls (left/right)
Light/dark modes: Built-in theme switching with automatic user preference detection
Custom CSS: Advanced styling via JavaScript SDK for design control beyond presets
Operating hours display: Show availability status to visitors automatically
Mobile responsiveness: Separate mobile widget settings with device-specific hiding options
Domain restrictions: Control which websites can embed widget through trusted domains configuration
Role-based access: Admin, Moderator, and Agent roles with configurable permissions (Growth+ plans) plus agent groups for departmental routing
White-labeling pricing: Note: $20/month addon on Growth tier OR included with Plus ($749+/month) - not available on Free/Starter
Custom avatars: Branded agent avatars and logos require Plus plans minimum
N/A
R A G Implementation & Accuracy
N/A
CRITICAL ARCHITECTURAL GAP: No NOT a RAG-as-a-Service platform - lacks vector databases, embedding controls, and configurable retrieval pipelines
Knowledge processing: Q&A extraction from URLs/PDFs/CSVs through opaque internal system without transparency into methodology
NO chunking parameters: No Chunk size, overlap, and strategy not exposed for optimization or tuning
NO embedding model selection: No Cannot choose between OpenAI, Cohere, or custom embedding models for vector generation
NO similarity threshold controls: No Cannot configure cosine similarity thresholds, retrieval scoring, or confidence levels
NO hybrid search: No No combination of keyword and semantic search strategies or BM25 integration
NO anti-hallucination mechanisms: No No citation attribution, source verification, or granular confidence scoring - responses cannot be traced to source documents
Hallucination prevention: Relies solely on strict knowledge base boundaries - Lyro answers only from provided sources and escalates when uncertain
Competitive positioning: Customer service automation platform, NOT autonomous knowledge retrieval system - fundamentally different architecture from RAG platforms (rated 2/10 as RAG platform)
N/A
Ease of Use & No- Code Interface ( Core Differentiator)
N/A
User satisfaction: 4.7/5 G2 rating with 1,600+ reviews citing exceptional usability as primary strength
45+ languages: English, Spanish, French, German, Italian, Portuguese, Dutch, Swedish, Norwegian, Polish, plus 35+ additional languages
Native processing: Lyro processes data sources directly in original language without internal English translation layer (reduces accuracy loss)
Automatic browser detection: Switches widget to visitor locale based on browser settings for seamless user experience
Multiple language packs: Allow department routing to language-specific teams for specialized support
Language limiting: Administrators can restrict which languages Lyro uses and set fallback behaviors for unsupported languages
20+ pre-translated packs: Chat widget language packs with manual translation options for additional coverage
Global reach advantage: Single knowledge base serves multiple languages vs competitors requiring separate configurations per locale (7.5/10 rated differentiator)
N/A
Customer Base & Case Studies
N/A
Scale: 300,000+ businesses served globally demonstrating SMB/e-commerce market fit
Named customers: Pizza Hut (89-90% automation rates), Decathlon, Casio (enterprise validation)
WordPress adoption: 60,000+ plugin installations demonstrate strong small business penetration
User satisfaction: 4.7/5 G2 rating (1,600+ reviews) with 68% five-star ratings
Review themes - Praise: Ease of use (253 mentions), easy setup (161 mentions), Shopify integration, visual Flow Builder, responsive support
Review themes - Criticisms: Analytics depth limitations, per-conversation pricing at scale, API access locked to Plus tier ($749/month), 10-operator cap on self-serve plans
Claude 3 upgrade impact: Success rates jumped from 50-70% to 79-87% with customer case studies reporting 89-90% automation after upgrade
N/A
Company Background
N/A
Founding: 2013 by Tytus Gołąs in Poland (12+ years of platform development and refinement)
After analyzing features, pricing, performance, and user feedback, both Botpress and Tidio are capable platforms that serve different market segments and use cases effectively.
When to Choose Botpress
You value visual drag-and-drop builder with extensive code extensibility via execute code cards
Massive scale validation: 750,000+ active bots, 1 billion+ messages processed
Comprehensive omnichannel support: WhatsApp, Slack, Teams, Telegram, Messenger, SMS, web
Best For: Visual drag-and-drop builder with extensive code extensibility via Execute Code cards
When to Choose Tidio
You value exceptional ease of use: 4.7/5 g2 rating with 253 'ease of use' and 161 'easy setup' mentions
Claude 3-powered Lyro AI achieving 79-87% success rates with customer case studies reporting 89-90% automation
300,000+ businesses served including Pizza Hut, Decathlon, Casio demonstrating SMB/e-commerce market fit
Best For: Exceptional ease of use: 4.7/5 G2 rating with 253 'Ease of Use' and 161 'Easy Setup' mentions
Migration & Switching Considerations
Switching between Botpress and Tidio requires careful planning. Consider data export capabilities, API compatibility, and integration complexity. Both platforms offer migration support, but expect 2-4 weeks for complete transition including testing and team training.
Pricing Comparison Summary
Botpress starts at custom pricing, while Tidio begins at $29/month. Total cost of ownership should factor in implementation time, training requirements, API usage fees, and ongoing support. Enterprise deployments typically see annual costs ranging from $10,000 to $500,000+ depending on scale and requirements.
Our Recommendation Process
Start with a free trial - Both platforms offer trial periods to test with your actual data
Define success metrics - Response accuracy, latency, user satisfaction, cost per query
Test with real use cases - Don't rely on generic demos; use your production data
Evaluate total cost - Factor in implementation time, training, and ongoing maintenance
Check vendor stability - Review roadmap transparency, update frequency, and support quality
For most organizations, the decision between Botpress and Tidio comes down to specific requirements rather than overall superiority. Evaluate both platforms with your actual data during trial periods, focusing on accuracy, latency, ease of integration, and total cost of ownership.
📚 Next Steps
Ready to make your decision? We recommend starting with a hands-on evaluation of both platforms using your specific use case and data.
• Review: Check the detailed feature comparison table above
• Test: Sign up for free trials and test with real queries
• Calculate: Estimate your monthly costs based on expected usage
• Decide: Choose the platform that best aligns with your requirements
Last updated: December 11, 2025 | This comparison is regularly reviewed and updated to reflect the latest platform capabilities, pricing, and user feedback.
The most accurate RAG-as-a-Service API. Deliver production-ready reliable RAG applications faster. Benchmarked #1 in accuracy and hallucinations for fully managed RAG-as-a-Service API.
DevRel at CustomGPT.ai. Passionate about AI and its applications. Here to help you navigate the world of AI tools and make informed decisions for your business.
People Also Compare
Explore more AI tool comparisons to find the perfect solution for your needs
Join the Discussion
Loading comments...