Progress Agentic RAG vs Stonly

Make an informed decision with our comprehensive comparison. Discover which RAG solution perfectly fits your needs.

Priyansh Khodiyar's avatar
Priyansh KhodiyarDevRel at CustomGPT.ai

Fact checked and reviewed by Bill Cava

Published: 01.04.2025Updated: 25.04.2025

In this comprehensive guide, we compare Progress Agentic RAG and Stonly 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 Progress Agentic RAG and Stonly, 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 Progress Agentic RAG if: you value proprietary remi v2 model (30x faster inference) addresses hallucination problem with continuous quality monitoring - differentiated capability absent from most competitors
  • Choose Stonly if: you value exceptional ease of use - 4.8/5 g2 rating with intuitive visual editor praised in 32 reviews

About Progress Agentic RAG

Progress Agentic RAG Landing Page Screenshot

Progress Agentic RAG is enterprise application development and deployment platform. Enterprise RAG-as-a-Service platform launched Sept 2025 following Progress Software's acquisition of Barcelona-based Nuclia. Combines SOC2/ISO 27001 security with proprietary REMi evaluation model for continuous answer quality monitoring. Built on open-source NucliaDB (710+ GitHub stars) with Python/JavaScript SDKs. Starting at $700/month. Founded in 2019 (Nuclia), acquired 2025, headquartered in Barcelona, Spain (Nuclia) / Bedford, MA, USA (Progress), the platform has established itself as a reliable solution in the RAG space.

Overall Rating
82/100
Starting Price
$700/mo

About Stonly

Stonly Landing Page Screenshot

Stonly is interactive knowledge base platform with enterprise ai-powered answers. Stonly is a customer support knowledge management platform with embedded AI capabilities focused on interactive step-by-step guides and help desk agent assistance. Its AI Answers feature (Enterprise-only add-on) achieves 71% self-serve success rates, but it's fundamentally a knowledge base platform with AI features—not a pure RAG-as-a-Service solution. Founded in 2017, headquartered in San Francisco, CA, the platform has established itself as a reliable solution in the RAG space.

Overall Rating
96/100
Starting Price
$249/mo

Key Differences at a Glance

In terms of user ratings, Stonly in overall satisfaction. From a cost perspective, Stonly offers more competitive entry pricing. The platforms also differ in their primary focus: Enterprise Software versus Knowledge Management. 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

logo of progress
Progress Agentic RAG
logo of stonly
Stonly
logo of customGPT logo
CustomGPTRECOMMENDED
Data Ingestion & Knowledge Sources
  • 60+ Document Formats: PDF, Word (.docx), Excel, PowerPoint, plain text, email formats with automatic parsing
  • Multimedia Processing: Automatic speech-to-text (MP3, WAV, AIFF), video transcript extraction (MP4, etc.), OCR for scanned documents/images
  • Cloud Connectors: SharePoint, Confluence, OneDrive, Google Drive, Amazon S3 with direct integration
  • Sync Agent Desktop App: 60-minute automatic sync with content hashing to prevent redundant reindexing
  • Manual Upload Interface: Files, folders, web links, sitemaps, Q&A pairs via dashboard
  • Fast Deployment: 2-hour initial ingestion, 48-hour full deployment timeline
  • CRITICAL GAPS: NO Dropbox integration, NO Notion integration, NO explicit YouTube transcript extraction documented
  • Architecture Focus: Comprehensive knowledge retrieval vs lead conversion focus (unlike Drift)
  • PDF uploads confirmed
  • Public website crawling: Pages not requiring authentication
  • Zendesk help center content indexing
  • Proprietary interactive guide format as primary content model
  • Note: No Google Drive, Dropbox, Notion, or SharePoint integrations for data ingestion
  • Note: No YouTube transcript extraction (videos can be embedded but not processed)
  • Note: No direct Word document (.docx) or HTML file imports confirmed
  • Note: No automatic content syncing from external sources - updates are manual through Stonly's visual editor
  • Content limits by tier: Basic (5 guides, 400 views/mo), Small Business (unlimited guides, 4K views/mo), Enterprise (custom)
  • Content versioning: Side-by-side comparison and instant restore on Business and Enterprise plans
  • 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
  • Python SDK: pip install nuclia (Python 3.8+, ~21,000 weekly downloads)
  • JavaScript/TypeScript SDK: @nuclia/core on NPM (React, Next.js, Angular, Vue.js, Svelte)
  • CMS Plugins: WordPress, Strapi integrations
  • Workflow Automation: Pipedream official app, Zapier API-compatible
  • Chrome Extension: Web page indexing capability
  • Progress Ecosystem: OpenEdge database connector, Sitefinity CMS integration ('first Generative CMS')
  • CRITICAL LIMITATION: NO native Slack, WhatsApp, Telegram, or Microsoft Teams integrations
  • Platform Design: RAG backend + embeddable widget, NOT omnichannel conversational AI platform
  • Custom Development Required: Messaging platform integrations need API-based custom builds
  • Deep help desk integrations: Zendesk, Salesforce Service Cloud, Freshdesk, ServiceNow
  • Zendesk features: Update tickets from guides, preserve guide progress in tickets, launch Zendesk Chat from widget
  • Zapier integration: Webhook triggers for form submissions and guide completions
  • Analytics integrations: Segment, Google Analytics
  • Embedding options: JavaScript widget, iframe, API deployment
  • Note: No native Slack, WhatsApp, Telegram, or Microsoft Teams integrations (confirmed by multiple user reviews)
  • Note: No omnichannel messaging support
  • Website embedding: All plans support JS widget and iframe embedding
  • 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.
  • Supports OpenAI API Endpoint compatibility. Read more here.
Core Chatbot Features
  • AI Search & Generative Answers: Semantic search and Q&A across knowledge bases with trusted, source-linked answers
  • Multi-Turn Conversations: Context-aware dialogue with conversation history maintained for follow-up questions
  • Source Citations: Every answer includes citations linking to source documents for verification and transparency
  • Auto-Summarization: Automatic summarization of long documents for quick understanding
  • Entity Recognition: AI classification and entity extraction enriching corpus for better Q&A
  • Answer-Only Mode: Widget configuration for concise answers vs detailed responses based on use case
  • Multilingual Support: Nuclia multilingual embedding model handles multiple languages out-of-box
  • MISSING FEATURES: NO lead capture, NO human handoff/escalation workflows, NO chat history export for users
  • Interactive step-by-step guides: Visual flow builder for creating structured content paths
  • Decision trees and branching logic: Guide users through complex troubleshooting with intelligent path selection
  • Checklists and task management: Help users complete multi-step processes with progress tracking
  • Contact forms and lead capture: Integrated forms for collecting customer information during interactions
  • Content versioning: Side-by-side comparison and instant restore on Business and Enterprise plans for content management
  • Multi-language support: Auto-translation on Enterprise plan for global deployments
  • Knowledge bases: 3 on Small Business plan, unlimited on Enterprise for organizing content
  • Guide views tracking: 400 (Free), 4,000 (Small Business), custom (Enterprise) for monitoring usage
  • NPS surveys: Available on all plans for measuring customer satisfaction
  • CSAT and CES surveys: Enterprise only for comprehensive satisfaction and effort measurement
  • 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.
Core Agent Features
  • Retrieval Agents: Autonomously select optimal retrieval strategies based on query characteristics
  • Pre-Built Ingestion Agents (Beta): Labeler (auto-classification), Generator (summaries/JSON/extraction), Graph Extraction (entities/relationships), Q&A Generator (automatic FAQ), Content Safety (inappropriate content flagging)
  • Web Components: <nuclia-search-bar> and <nuclia-chat> for website embedding
  • Widget Configuration: Point-and-click for suggestions, filters, metadata display, thumbnails, answer-only modes
  • CSS Customization: Shadow DOM architecture with cssPath attribute for advanced styling
  • White-Labeling: Full OEM deployment support via API-first design
  • MISSING FEATURES: NO lead capture, NO human handoff/escalation workflows, NO proactive alerting (monitoring exists, alerting undocumented)
  • Conversational AI Bot: Delivers confident answers backed by verified structured knowledge unlike generic LLMs that can hallucinate or invent answers
  • Knowledge-grounded responses: Provides answers backed by verified structured knowledge from guides you create preventing fabricated information
  • AI Agent Assist: Automatically summarizes tickets, suggests right path to resolution, and generates responses for support agents
  • Three core automation functions: Automatically analyzes and summarizes support ticket content, recommends most relevant Stonly guide/knowledge path to resolve issues, drafts complete responses for agents to review/edit/send
  • Process automation: Define processes to be followed and link them to different back-office tools to resolve customer requests before they reach support
  • Personalized knowledge: AI-powered solutions and process automation allow creation of guides, walkthroughs, checklists, knowledge bases adapting to each customer's needs
  • 71% self-serve success rate: With AI Answers feature documented in company data
  • Hallucination reduction: Knowledge-grounding approach vs generic chatbots reduces off-topic responses
  • 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
Additional Considerations
  • Recent Acquisition (June 2025): Progress Software acquired Nuclia for $50M - platform transitioning under new ownership with potential strategic direction changes
  • Genuine No-Code + Developer Appeal: Dual-track value proposition - non-technical teams use dashboard, developers leverage API/SDKs for custom builds
  • REMi Quality Differentiator: Proprietary continuous evaluation model (30x faster in v2) addresses hallucination problem absent from most RAG competitors
  • Open-Source Trust Factor: NucliaDB (710+ GitHub stars, AGPLv3) provides code transparency vs black-box platforms - security audits possible
  • Multimodal Strength: OCR for images, speech-to-text for audio/video creates comprehensive searchable corpus beyond text-only competitors
  • Enterprise RAG Focus: Platform optimized for knowledge retrieval and semantic search - not conversational marketing/sales engagement like Drift/Yellow.ai
  • Progress Ecosystem Integration: OpenEdge database connector, Sitefinity CMS integration provides distribution channels unavailable to standalone platforms
  • Documentation Fragmentation: Dual portals (docs.rag.progress.cloud + legacy docs.nuclia.dev) during transition may cause developer confusion
  • Competitive Pricing Entry: $700/month Fly tier undercuts enterprise RAG alternatives while providing genuine capabilities vs limited free tiers
  • Best For: Organizations wanting model flexibility (7 providers), multimodal indexing, open-source transparency, and developer API access without managing infrastructure
  • Limited UI customization: Limited ability to customize user interface and workflows to match specific brand requirements is primary user concern
  • Basic collaboration tools: Without real-time editing or advanced team management features can hinder team productivity when multiple people need to work together
  • No offline access: Guides unavailable without internet connectivity reducing usability in areas with unreliable internet
  • Performance degradation: Can degrade with very large or complex guides causing slower responsiveness indicating scalability concerns
  • Restricted language options: Limit efficient creation of multilingual content which may be barrier for global organizations
  • Mixed media support missing: Users find missing features wishing for mixed media support and enhanced reporting tools
  • Step ordering difficulties: Users report limitations in feature usability and difficulties with step ordering though support offers helpful workarounds
  • Requires coding knowledge: Unlike most competitors, doesn't advertise as no-code platform - need coding knowledge to track events, target users, stream data, and style content
  • Image workflow limitations: Inability to use images in base offering limits utility in some workflows with some advanced features requiring extra costs
  • View-based pricing: Charges additional fees based on guide views - customers exceeding 4,000 guide views/month pay extra $250-500 monthly depending on volume
  • Integration reliability: Users find lack of integrations limits ability to fully connect Stonly with other tools - Stonly/Zendesk integration isn't as reliable as desired (stops working every few weeks)
  • 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.
Customization & Branding
  • Prompt Lab: Test LLMs side-by-side using actual customer data with real-time comparison
  • 30+ RAG Parameters: Custom chunking strategies, context size configuration, hybrid search weighting
  • Retrieval Strategy Customization: Agents autonomously select optimal approaches per query
  • Widget Customization: Visual editor for suggestions, filters, metadata, thumbnails, answer modes
  • Advanced CSS Styling: Shadow DOM with cssPath attribute for deep customization
  • White-Labeling Support: Full OEM deployments via API-first architecture
  • Role-Based Access Control: Account-level (Owners, Members), Knowledge Box-level (Manager, Writer, Reader) with cascading permissions
  • SSO Integration: Enterprise identity provider connectivity
  • Visual editor: Intuitive no-code interface for creating guides, decision trees, checklists, forms
  • CSS customization: Available on all paid plans
  • White-labeling: Enterprise plan only - complete branding removal
  • Pre-built templates: Common support scenarios covered
  • Role-based access control: Advanced permissions on Enterprise plan
  • Learning curve: Described as "small" - users can create guides in under 30 minutes
  • Note: No formal content approval workflows documented
  • Note: Cannot edit guides on mobile devices
  • Note: Angular framework compatibility issues reported - "Stonly onboarding will work randomly" with dynamic code
  • 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.
L L M Model Options
  • Anthropic: Claude 3.7, Claude 3.5 Sonnet v2
  • OpenAI: ChatGPT 4o, 4o mini
  • Google: Gemini Flash 2.5, Palm2
  • Meta: Llama 3.2
  • Microsoft/Azure: Mistral Large 2
  • Cohere: Command-R suite
  • Nuclia Private GenAI: 100% data isolation for maximum security
  • Model Switching: Change providers without architectural changes via Prompt Lab
  • Embedding Flexibility: Configurable per Knowledge Box (Nuclia multilingual default + OpenAI embeddings)
  • Side-by-Side Testing: Compare responses across models using actual data in Prompt Lab
  • Note: Undisclosed proprietary LLM - Stonly does not disclose the specific model powering AI Answers
  • Note: No model selection - users cannot choose between GPT-3.5, GPT-4, Claude, or other models
  • Note: No temperature controls, fine-tuning, or model routing
  • AI Profiles: Up to 20 per team for tone and behavior customization
  • Custom Instructions: Up to 100 per team defining boundaries and style
  • Guided AI Answers: Define specific questions that trigger predetermined answers, bypassing AI generation for sensitive scenarios
  • Automatic fallback: When AI confidence is low, system falls back to ML-powered search rather than forcing an answer
  • Knowledge-grounded approach: AI responses anchored in Stonly guides, external websites, and selected PDFs to reduce hallucinations
  • 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)
  • Open-Source Foundation: NucliaDB (710+ GitHub stars, AGPLv3 license, Python/Rust) provides transparency into core retrieval mechanisms
  • Python SDK: pip install nuclia (Python 3.8+, ~21,000 weekly downloads) - full API coverage
  • JavaScript/TypeScript SDK: @nuclia/core (React, Next.js, Angular, Vue.js, Svelte support)
  • REST API: Regional endpoints https://{region}.rag.progress.cloud/api/v1/ with comprehensive documentation
  • Key Endpoints: /ask (generative answers), /find (semantic search), /upload (ingestion), /remi (quality evaluation)
  • Dual Documentation: docs.rag.progress.cloud (primary) + legacy docs.nuclia.dev (fragmentation concern)
  • RAG Cookbook: Downloadable comprehensive guide for developers
  • Code Example Simplicity: Upload and search in just a few Python lines with intuitive SDK design
  • API-First Design: Complete programmatic control over all platform capabilities
  • REST API: Supports user provisioning, content management, widget control
  • Mobile SDKs (Enterprise only): iOS, Android, React Native, Flutter
  • Note: No Python SDK or server-side Node.js SDK
  • Note: No GraphQL API or OpenAPI/Swagger specification
  • Note: Rate limits not publicly documented
  • Note: No API Explorer, sandbox environment, or Postman collections
  • Note: REST API versioning strategy unclear
  • Widget API: Programmatic control including opening specific content, listening for events, user identification
  • CSP whitelisting: Instructions documented for Content Security Policy compliance
  • Widget versioning documented
  • Ships a well-documented REST API for creating agents, managing projects, ingesting data, and querying chat. API Documentation
  • Offers open-source SDKs—like the Python customgpt-client—plus Postman collections to speed integration. Open-Source SDK
  • Backs you up with cookbooks, code samples, and step-by-step guides for every skill level.
Performance & Accuracy
  • Benchmark Leader: Nuclia with OpenAI embeddings achieved highest scores vs Vectara on Docmatix 1.4k dataset across answer relevance, context relevance, correctness
  • 100M Vectors: Fully ingested and optimized in ~20 minutes with sufficient worker allocation
  • REMi v2 Speed: 30x faster inference than original Mistral-based implementation (Llama 3.2-3B based)
  • Four-Index Hybrid Search: Document Index (property filtering), Full Text (keyword/fuzzy), Vector/Chunk (semantic), Knowledge Graph (entity relationships)
  • Dynamic Sharding: Automatic shard creation as vector counts grow with index node replication for fault tolerance
  • Fast Deployment: 2-hour initial ingestion, 48-hour full deployment timeline
  • ACID Compliance: TiKV key-value store (Tier 2) manages resource metadata with transaction guarantees
  • Three-Tier Storage: Tier 3 (S3/GCS blobs), Tier 2 (TiKV metadata), Tier 1 (sharded indexes)
  • 71% self-serve success rate with AI Answers feature (company data)
  • 70-76% support ticket reduction documented in case studies
  • 99.9% uptime claimed but no published SLA details or response time data
  • Note: No published latency metrics or performance benchmarks
  • Note: No real-time analytics - Flow reports update every 15 minutes
  • Hallucination controls: Strong grounding in structured content reduces off-topic responses
  • Widget lazy loading: Minimizes impact on host website performance
  • 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 ( Behavior & Knowledge)
  • 30+ RAG Optimization Parameters: Fine-grained control over retrieval behavior
  • Custom Chunking Strategies: Configurable text segmentation for optimal context windows
  • Context Size Configuration: Adjust context sent to LLMs based on use case
  • Hybrid Search Weighting: Balance keyword vs semantic search relevance
  • Retrieval Agent Autonomy: Automatically select optimal strategies per query characteristics
  • Embedding Model Flexibility: Switch per Knowledge Box (Nuclia multilingual + OpenAI options)
  • Prompt Lab Experimentation: Test configurations with actual data before production deployment
  • LLM Provider Switching: Change models without architectural changes (7 providers supported)
  • CSS and HTML customization: Change layout and look of knowledge base with custom code capabilities
  • Intuitive customization tools: Easy-to-use tools that don't require code for basic customization
  • Layout customization: Decide how content is structured and presented with flexible options
  • Design controls: Manage visual components like colors, logo, or cover image for brand alignment
  • Personalized content: Use customer data to show personalized content from knowledge base for targeted experiences
  • Data-driven personalization: Customers see what they need right away when first accessing knowledge base
  • Analytics insights: Guide usage analytics provide insight into customer behavior for continuous improvement
  • Highly flexible platform: Users appreciate ability to use Stonly for knowledge bases and guided tours with target properties based on specific user needs
  • Rich media support: Add images, GIFs, videos, and annotations to bring knowledge base content to life
  • Third-party scripts: Install scripts from other tools like Google Analytics for extended functionality
  • 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.
Pricing & Scalability
  • Fly Tier: $700/month - 10GB/15K resources, 750MB max file, 1 Knowledge Box, cloud only, 10K tokens/month
  • Growth Tier: $1,750/month - 50GB/80K resources, 1.5GB max file, 2 Knowledge Boxes, Prompt Lab, 10K tokens/month
  • Enterprise Tier: Custom pricing - Unlimited data/file size, 11 Knowledge Boxes, hybrid/on-prem deployment, 10K tokens/month
  • Token Consumption: $0.008/token beyond 10K/month included across all tiers
  • 14-Day Free Trial: Available without disclosed credit card requirement
  • AWS Marketplace: Simplifies enterprise procurement with existing cloud spend commitments
  • Competitive Entry Point: $700/month undercuts enterprise alternatives (Drift $30K+/year, Yellow.ai similar)
  • Scaling Consideration: Token-based consumption pricing requires careful usage forecasting for budget predictability
  • Basic (Free): 5 guides, 400 views/month, 1 seat, single language
  • Small Business ($249/mo, $199/mo annual): Unlimited guides, 4,000 views/month, 5 seats, 3 knowledge bases, CSS customization, Zapier, NPS surveys
  • Enterprise (Custom, ~$39K/year avg): Custom views, unlimited seats, AI Answers add-on, Mobile SDKs, SAML SSO, white-label, auto-translation, CSAT/CES surveys
  • Overage pricing escalates quickly: +15K views = $200/month, +30K views = $400/month
  • Automatic tier upgrades: Exceeding limits for 2 consecutive months triggers upgrade
  • Note: AI Answers, Mobile SDK, SAML SSO, white-labeling all Enterprise-gated
  • Average enterprise contract: ~$39,000 annually according to Vendr procurement data
  • 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
  • SOC2 Type 2 Certified: Annual audits for enterprise security assurance
  • ISO 27001 Certified: Annually audited information security management
  • GDPR Compliant: Built-in PII anonymization automatically detects and removes personal data
  • Encryption: AES-256 at rest, TLS in transit for comprehensive data protection
  • AI Risk Classification: Low to minimal AI risk category with policy-as-code guardrails
  • Human-in-the-Loop: Validation options for critical workflows
  • Tenant Isolation: Customer data separation ensures multi-tenant security
  • Audit Logs: Standard across all pricing tiers for compliance tracking
  • API Key Management: Temporal keys and rotation for security hygiene
  • CRITICAL: CRITICAL LIMITATION: NO HIPAA certification documented - healthcare organizations processing PHI must contact sales for compliance clarification
  • Data Governance: Enterprise tier supports complete on-premise deployment for 100% data control
  • Yes SOC 2 Type 2
  • Yes GDPR compliant
  • Yes HIPAA compliant
  • Yes ISO 27001
  • Yes PCI compliant
  • Yes CSA Star Level 1
  • Trust Center: trust.stonly.com with security documentation, subprocessor lists, controls information
  • SAML 2.0 SSO: Enterprise plan
  • IP allowlisting: Enterprise plan
  • Advanced RBAC: Enterprise plan
  • Two-factor authentication: SMS, email, hardware tokens, TOTP, U2F
  • Note: Data residency options not documented
  • Note: No explicit documentation on customer data usage for AI model training
  • International data transfers: Standard Contractual Clauses for EU compliance
  • 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.
Observability & Monitoring
  • REMi Real-Time Dashboard: Answer relevance, context relevance, groundedness, correctness (0-5 scale)
  • 7-Day Rolling Averages: Performance evolution graphs spanning 24 hours to 30 days
  • Health Displays: Quality metrics shown in real-time for immediate visibility
  • Four Quality Dimensions: Answer Relevance (query alignment), Context Relevance (passage quality), Groundedness (source derivation), Answer Correctness (ground truth alignment)
  • REMi v2 Performance: 30x faster inference (Llama 3.2-3B) vs original Mistral implementation
  • Benchmark Validation: Tested against Vectara on Docmatix 1.4k dataset with highest scores
  • Audit Logs: Standard across all tiers for compliance and security tracking
  • MISSING FEATURE: Proactive alerting not documented (monitoring exists, automated alerts unclear)
  • Insights Dashboard: Guide views, unique visitors, bounce rates, step-by-step progression, drop-off analysis
  • NPS surveys: All plans
  • CSAT and CES surveys: Enterprise only
  • Flow reports: Update every 15 minutes (not real-time)
  • Data export: Integration with Segment, Zapier, Google Analytics
  • Note: No real-time visitor tracking
  • Note: No predictive analytics
  • Note: Basic compared to dedicated product analytics tools
  • Note: No heatmaps or A/B testing capabilities
  • Agent performance tracking: Relies on external help desk platform integration rather than native dashboards
  • 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
  • Dual Documentation Portals: docs.rag.progress.cloud (primary) + legacy docs.nuclia.dev (fragmentation concern)
  • RAG Cookbook: Comprehensive downloadable guide for developers
  • SDK Ecosystem: Python (~21K weekly downloads) + JavaScript/TypeScript with active developer usage
  • 14-Day Free Trial: Hands-on evaluation without credit card requirement
  • Progress Enterprise Support: Backed by 2,000+ employee parent company infrastructure
  • AWS Marketplace: Available November 2025 for streamlined enterprise procurement
  • Open-Source Community: NucliaDB 710+ GitHub stars with AGPLv3 license transparency
  • API-First Support: Comprehensive REST API documentation with regional endpoints
  • 4.8/5 G2 rating (132 reviews)
  • Ease of use praised in 32 G2 reviews
  • Help Center documentation
  • Email and chat support
  • Dedicated support: Enterprise plan
  • Learning resources: Pre-built templates, tutorials
  • Quick onboarding: Users report creating guides in under 30 minutes
  • 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
  • Target Users: Non-technical teams (marketing, HR, legal, customer support) with zero coding required
  • Visual Dashboard: Create Knowledge Box, upload documents, deploy search widget in single session
  • Point-and-Click Widget Editor: Configure suggestions, filters, metadata, thumbnails, answer modes visually
  • Pre-Built Ingestion Agents (Beta): Automated workflows for labeling, summarization, graph extraction, Q&A generation, content safety
  • Prompt Lab: Visual interface for side-by-side LLM testing with actual data
  • Role-Based Access Control: Visual permission management separating Account and Knowledge Box concerns
  • Rapid Deployment: Progress explicitly markets minutes-to-production capability for business users
  • Shadow DOM Architecture: Advanced users can apply CSS styling via cssPath attribute for customization
  • 4.8/5 ease of use rating on G2
  • "Ease of use" mentioned 32 times in G2 reviews
  • Visual drag-and-drop editor requires no coding
  • Small learning curve - non-technical teams productive quickly
  • Guide creation in under 30 minutes reported by users
  • Pre-built templates for common scenarios
  • Intuitive interface for support teams
  • Note: Some navigation confusion reported in admin interface
  • Note: Cannot edit on mobile devices
  • 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 E Mi Evaluation Model ( Core Differentiator)
  • Proprietary Investment: Significant R&D differentiator addressing hallucination problem - absent from most competitors
  • REMi v2 (Current): Llama-REMi v1 based on Llama 3.2-3B with 30x faster inference vs original Mistral implementation
  • Continuous Quality Monitoring: Evaluates EVERY interaction across four dimensions (0-5 scale)
  • Answer Relevance: Measures how directly response addresses the query
  • Context Relevance: Assesses quality of retrieved passages relative to question
  • Groundedness: Evaluates degree to which answers derive from source context (hallucination detection)
  • Answer Correctness: Alignment with ground truth when available (optional dimension)
  • Benchmark Validation: Nuclia with OpenAI embeddings achieved highest scores vs Vectara on Docmatix 1.4k dataset across answer relevance, context relevance, correctness
  • Real-Time Visibility: Dashboard health displays with 7-day rolling averages and performance graphs (24h to 30d)
  • Competitive Advantage: Most RAG platforms lack continuous quality evaluation - Progress makes this core differentiator
N/A
N/A
Open- Source Nuclia D B Foundation
  • GitHub Presence: 710+ stars, AGPLv3 license provides full transparency into core retrieval mechanisms
  • Technology Stack: Python and Rust implementation for performance and reliability
  • Managed Infrastructure: Progress removes operational burden while maintaining technical transparency
  • Three-Tier Storage: Tier 3 (S3/GCS blob storage), Tier 2 (TiKV key-value with ACID), Tier 1 (sharded indexes)
  • Four Index Types: Document Index (property filtering), Full Text (keyword/fuzzy search), Chunk/Vector (semantic similarity), Knowledge Graph (entity relationships)
  • Dynamic Sharding: Automatic shard creation as vectors grow with index node replication for fault tolerance
  • Embedding Flexibility: Switchable per Knowledge Box (Nuclia multilingual + OpenAI options)
  • 100M Vector Performance: Full ingestion and optimization in ~20 minutes with sufficient worker allocation
  • Developer Trust: Open-source foundation allows code inspection and contribution vs black-box competitors
N/A
N/A
Multi- Lingual Support
  • Nuclia Multilingual Embedding Model: Default model supporting multiple languages out-of-box
  • 60+ Document Format Processing: Multi-language content across PDF, Word, Excel, PPT, text, email
  • Automatic Transcription: Multi-language speech-to-text for audio/video content
  • Configurable Embeddings: Per Knowledge Box language optimization
  • LLM Provider Flexibility: 7 providers with varying multilingual capabilities (Claude, GPT, Gemini, Llama, etc.)
  • Global Customer Base: Deployed across Spain, US, international markets indicating production multilingual usage
N/A
N/A
R A G-as-a- Service Assessment
  • Platform Type: TRUE RAG-AS-A-SERVICE PLATFORM - Core mission is retrieval-augmented generation backend with developer-first API access
  • Core Focus: Semantic search and generative Q&A across knowledge bases with transparent NucliaDB architecture
  • RAG Backend Design: Fully managed RAG infrastructure with embeddable widgets (NOT closed conversational marketing like Drift/Yellow.ai)
  • Programmatic Access: Complete REST API + dual SDKs (Python/JavaScript) for full knowledge base management
  • LLM Flexibility: 7 provider options switchable without architectural changes (Anthropic, OpenAI, Google, Meta, Cohere, Azure, Nuclia)
  • Open-Source Transparency: NucliaDB foundation (710+ GitHub stars) provides visibility into retrieval mechanisms vs black-box platforms (Lindy.ai)
  • Comparison Alignment: Direct architectural comparison to CustomGPT.ai is valid - both are RAG-as-a-Service platforms with API-first design
  • Use Case Fit: Organizations prioritizing knowledge retrieval, semantic search, and generative Q&A over conversational marketing/sales engagement
  • Note: NOT a RAG-as-a-Service platform - fundamentally a knowledge base tool with embedded AI
  • Data source flexibility: Limited (PDF, public web, Zendesk only) vs comprehensive RAG platforms
  • LLM model options: None (undisclosed proprietary model, no user selection)
  • API-first architecture: Weak (widget-focused, limited SDKs, no server-side SDKs)
  • Performance benchmarks: Not published
  • Self-service AI pricing: Not available (Enterprise-gated, ~$39K/year)
  • Help desk integration depth: Excellent (best-in-class Zendesk, Salesforce, Freshdesk)
  • Hallucination controls: Strong (grounded in structured content)
  • Best for: Customer support ticket deflection, not flexible RAG backends
  • Not ideal for: Developers seeking pure RAG API, multi-tenant SaaS RAG backends, use cases needing model selection/fine-tuning
  • Platform Type: TRUE RAG-AS-A-SERVICE PLATFORM - all-in-one managed solution combining developer APIs with no-code deployment capabilities
  • 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
  • Market Position: Enterprise RAG-as-a-Service with genuine no-code accessibility + developer-first API design (dual-track appeal)
  • Pricing Advantage: $700/month entry undercuts enterprise competitors (Drift $30K+/year, Yellow.ai similar, CustomGPT varies)
  • REMi Differentiator: Proprietary continuous quality monitoring addresses hallucination problem - capability absent from most competitors
  • Benchmark Leadership: Achieved highest scores vs Vectara on Docmatix 1.4k dataset (answer relevance, context relevance, correctness)
  • Open-Source Trust: NucliaDB transparency (710+ GitHub stars) vs black-box competitors (Lindy.ai, Drift, Yellow.ai)
  • vs. CustomGPT: Similar RAG-as-a-Service category, Progress emphasizes REMi quality monitoring + open-source foundation differentiation
  • vs. Drift/Yellow.ai: TRUE RAG platform vs conversational marketing/sales engagement platforms (fundamentally different categories)
  • vs. Lindy.ai: Full API/SDK access vs NO public API (Progress developer-friendly, Lindy no-code only)
  • Integration Gaps: NO native messaging channels (Slack/WhatsApp/Teams) vs omnichannel competitors - requires custom development
  • HIPAA Gap: No documented certification creates healthcare trust gap vs compliant competitors (Drift has HIPAA)
  • Recent Acquisition Risk: June 2025 Progress purchase means platform still maturing under new ownership with potential direction changes
  • Progress Ecosystem Advantage: Integration with OpenEdge, Sitefinity CMS provides distribution channels unavailable to standalone competitors
  • Unique strength: Interactive guide format for structured support content
  • vs CustomGPT: Not comparable - different product categories (knowledge base vs RAG-as-a-Service)
  • vs Zendesk: Lighter-weight alternative focused on self-service guides vs full customer service platform
  • vs traditional chatbots: Interactive guides provide structured paths vs free-form conversation
  • Target audience: Support teams using Zendesk/Salesforce, not developers building RAG applications
  • 70-76% ticket reduction documented in case studies
  • 71% self-serve success rate with AI Answers
  • Enterprise compliance suitable for regulated industries
  • 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
Deployment & Infrastructure
  • Fully Managed Cloud: EU (primary) and US data centers with regional API routing (https://{region}.rag.progress.cloud/api/v1/)
  • Hybrid Deployment: Cloud processing with on-premise NucliaDB storage for data sovereignty requirements
  • Complete On-Premise: Enterprise tier supports 100% on-premise deployment for maximum data governance
  • AWS Marketplace: Available November 2025 for streamlined enterprise procurement with existing cloud spend
  • Three-Tier Architecture: S3/GCS blob storage (Tier 3), TiKV metadata (Tier 2), sharded indexes (Tier 1)
  • Dynamic Scaling: Automatic shard creation as vector counts grow with index node replication
  • Web Component Embedding: <nuclia-search-bar> and <nuclia-chat> for website integration
  • Multi-Region Support: Regional data residency options (EU/US) for compliance requirements
N/A
N/A
Customer Base & Case Studies
  • SRS Distribution (Wholesale Building Materials): "Progress Agentic RAG has fundamentally changed how we access and act on information across our organisation. Its ability to deliver fast, accurate, and verifiable insights from our unstructured data has been a game-changer for productivity and decision-making."
  • BrokerChooser (Financial Services): Replaced keyword search with generative AI, reporting significant conversion increases and better user experience
  • NAFEMS (Engineering Simulation Association): Knowledge discovery across thousands of technical publications for international membership community
  • Althaia Hospitals (Spain's Largest Central Catalonia Hospital): Medical protocol search supporting 5,000+ healthcare professionals
  • Columbia Business School: Academic knowledge discovery and research support
  • Barry University: Education sector deployment for institutional knowledge management
  • CCOO (Spain's Largest Trade Union): 1M+ members served with knowledge retrieval platform
  • Buff Sportswear: Commercial deployment for product and customer knowledge management
  • Pre-Acquisition Scale: ~20 customers across healthcare, pharmaceutical, education, public administration sectors
N/A
N/A
A I Models
  • Anthropic Models: Claude 3.7, Claude 3.5 Sonnet v2 for safety-focused, high-quality generation
  • OpenAI Models: ChatGPT 4o, 4o mini for industry-leading language capabilities
  • Google Models: Gemini Flash 2.5, PaLM2 for multimodal and search-optimized tasks
  • Meta Models: Llama 3.2 for open-source flexibility and customization
  • Microsoft/Azure: Mistral Large 2 for enterprise deployments with Azure integration
  • Cohere Models: Command-R suite for retrieval-optimized generation
  • Nuclia Private GenAI: 100% data isolation mode for maximum security without third-party LLM exposure
  • Model Switching: Change providers without architectural changes via Prompt Lab for side-by-side testing
  • Embedding Flexibility: Configurable per Knowledge Box (Nuclia multilingual default + OpenAI embeddings)
  • Undisclosed Proprietary LLM: Stonly does not publicly disclose the specific model powering AI Answers feature
  • No Model Selection: Users cannot choose between GPT-3.5, GPT-4, Claude, Gemini, or other LLM providers
  • No Temperature Controls: No user-facing controls for adjusting response creativity, randomness, or formatting
  • No Fine-Tuning or Model Routing: Cannot customize model behavior beyond predefined AI Profiles and Custom Instructions
  • AI Profiles (Up to 20): Define tone, boundaries, and behavior for different use cases or audiences
  • Custom Instructions (Up to 100): Set specific rules and style guidelines for AI response generation
  • Guided AI Answers: Predefined responses for specific questions bypassing AI generation for sensitive scenarios
  • Automatic Fallback: Low-confidence scenarios trigger fallback to ML-powered search rather than forcing unreliable AI answer
  • Knowledge-Grounded Approach: AI responses anchored in Stonly guides, external websites, and PDFs to reduce hallucinations
  • 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
R A G Capabilities
  • Agentic RAG Engine: Retrieval agents autonomously select optimal strategies based on query characteristics
  • Four-Index Hybrid Search: Document (property filtering), Full Text (keyword/fuzzy), Vector/Chunk (semantic), Knowledge Graph (entity relationships)
  • 30+ RAG Parameters: Custom chunking strategies, context size configuration, hybrid search weighting for fine-tuned optimization
  • REMi v2 Quality Monitoring: Continuous evaluation across Answer Relevance, Context Relevance, Groundedness, Correctness (30x faster inference)
  • Benchmark Leadership: Highest scores vs Vectara on Docmatix 1.4k dataset (answer relevance, context relevance, correctness)
  • Pre-Built Ingestion Agents (Beta): Labeler (auto-classification), Generator (summaries/JSON), Graph Extraction (entities/relationships), Q&A Generator, Content Safety
  • Multimodal Processing: OCR for scanned documents/images, automatic speech-to-text for audio (MP3, WAV, AIFF), video transcript extraction
  • 60+ Document Formats: PDF, Word, Excel, PowerPoint, plain text, email formats with automatic parsing
  • Open-Source Foundation: NucliaDB (710+ GitHub stars, AGPLv3) provides transparency into retrieval mechanisms vs black-box platforms
  • AI Answers (Enterprise Add-On): Generative AI responses grounded in Stonly guides, external websites, and selected PDFs
  • Knowledge-Grounding: Responses anchored to structured content (interactive guides, decision trees, checklists) reducing hallucinations vs generic chatbots
  • Confidence-Based Fallback: Automatic switch to ML-powered search when AI confidence is low preventing unreliable answers
  • Multi-Source Ingestion: PDF uploads, public website crawling, Zendesk help center content indexing
  • Interactive Guide Format: Proprietary content model combining structured workflows with AI-generated answers
  • Limited Data Sources: No Google Drive, Dropbox, Notion, SharePoint, or YouTube transcript extraction
  • Manual Content Updates: Updates through Stonly's visual editor—no automatic syncing from external sources
  • 71% Self-Serve Success Rate: Documented effectiveness of AI Answers in reducing support escalations
  • Hallucination Controls: Strong grounding in structured content vs open-ended conversational AI
  • 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
Use Cases
  • Enterprise Knowledge Management: Non-technical teams (marketing, HR, legal, customer support) deploying knowledge bases in minutes
  • Healthcare & Pharma: Althaia Hospitals medical protocol search for 5,000+ healthcare professionals with HIPAA-grade security needs
  • Financial Services: BrokerChooser replaced keyword search with generative AI for significant conversion increases
  • Education: Columbia Business School and Barry University for academic knowledge discovery and institutional knowledge management
  • Engineering & Research: NAFEMS knowledge discovery across thousands of technical publications for international membership
  • Trade Organizations: CCOO (Spain's largest union) serving 1M+ members with knowledge retrieval platform
  • Intelligent Document Processing: Automatic document classification, routing, extraction, risk identification, and summary generation
  • Dynamic Knowledge Management: Continuous updates, gap identification, and automatic documentation generation
  • Developer RAG Backend: API-first infrastructure for building custom AI applications with Prompt Lab experimentation
  • Customer Support Ticket Deflection: 70-76% ticket reduction through interactive self-service guides and AI Answers
  • Help Desk Integration: Deep Zendesk, Salesforce Service Cloud, Freshdesk, ServiceNow integration for unified support workflows
  • Interactive Onboarding: Step-by-step guides, decision trees, and checklists for product onboarding and user education
  • Knowledge Base Enhancement: Augment traditional help centers with interactive guides and AI-powered search
  • Agent Assistance: Provide support agents with guided workflows and AI answers during live interactions
  • Multi-Language Support: Auto-translation on Enterprise plan for global support teams and multilingual customers
  • Complex Troubleshooting: Decision tree logic guides users through multi-step troubleshooting processes
  • Compliance & Training: Structured guides ensuring consistent information delivery for regulated industries
  • 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)
  • Financial services: Product guides, compliance documentation, customer education with GDPR compliance
  • E-commerce: Product recommendations, order assistance, customer inquiries with API integration to 5,000+ apps via Zapier
  • SaaS onboarding: User guides, feature explanations, troubleshooting with multi-agent support for different teams
Security & Compliance
  • SOC2 Type 2: Annually audited for enterprise security assurance
  • ISO 27001: Annually audited information security management certification
  • GDPR Compliant: Built-in PII anonymization automatically detects and removes personal data
  • Encryption: AES-256 at rest, TLS in transit for comprehensive data protection
  • AI Risk Classification: Low to minimal AI risk category with policy-as-code guardrails
  • Human-in-the-Loop: Validation options for critical workflows requiring human oversight
  • Tenant Isolation: Customer data separation ensures multi-tenant security with isolated Knowledge Boxes
  • Audit Logs: Standard across all pricing tiers for compliance tracking and security monitoring
  • API Key Management: Temporal keys and rotation for security hygiene
  • CRITICAL LIMITATION: NO HIPAA certification documented - healthcare organizations processing PHI must contact sales for compliance clarification
  • Data Governance: Enterprise tier supports complete on-premise deployment for 100% data control and sovereignty
  • SOC 2 Type 2: Service Organization Control certification for security, availability, and confidentiality
  • GDPR Compliant: European data protection regulation compliance with data processing agreements
  • HIPAA Compliant: Healthcare data protection requirements for medical organizations and patient information
  • ISO 27001: International information security management system standard
  • PCI Compliant: Payment Card Industry Data Security Standard for handling payment information
  • CSA Star Level 1: Cloud Security Alliance STAR self-assessment certification
  • Trust Center: Public trust.stonly.com with security documentation, subprocessor lists, and controls information
  • SAML 2.0 SSO (Enterprise): Single sign-on integration with enterprise identity providers
  • IP Allowlisting (Enterprise): Restrict access to specific IP ranges for enhanced security
  • Advanced RBAC (Enterprise): Role-based access control with granular permissions and activity tracking
  • Two-Factor Authentication: SMS, email, hardware tokens, TOTP, U2F for account security
  • International Data Transfers: Standard Contractual Clauses for EU compliance and data protection
  • Data Residency: Options not publicly documented—may limit deployment in certain jurisdictions
  • 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
  • Fly Tier: $700/month - 10GB/15K resources, 750MB max file, 1 Knowledge Box, cloud only, 10K tokens/month included
  • Growth Tier: $1,750/month - 50GB/80K resources, 1.5GB max file, 2 Knowledge Boxes, Prompt Lab access, 10K tokens/month
  • Enterprise Tier: Custom pricing - Unlimited data/file size, 11 Knowledge Boxes, hybrid/on-prem deployment, 10K tokens/month
  • Token Consumption: $0.008/token beyond 10K/month included across all tiers for usage-based scaling
  • 14-Day Free Trial: Available without disclosed credit card requirement for hands-on evaluation
  • AWS Marketplace: Available November 2025 for simplified enterprise procurement with existing cloud spend commitments
  • Competitive Entry Point: $700/month undercuts enterprise alternatives (Drift $30K+/year, Yellow.ai similar, LiveChat per-agent scaling)
  • Scaling Consideration: Token-based consumption pricing requires careful usage forecasting for budget predictability beyond included tier
  • Best Value For: Organizations wanting to control costs through usage optimization vs fixed seat-based or per-project pricing models
  • Basic (Free): 5 guides, 400 views/month, 1 seat, single language, Stonly branding
  • Small Business ($249/mo or $199/mo annual): Unlimited guides, 4,000 views/month, 5 seats, 3 knowledge bases, CSS customization, Zapier, NPS surveys
  • Enterprise (Custom, ~$39K/year avg): Custom views, unlimited seats, white-label, SAML SSO, auto-translation, CSAT/CES surveys, Mobile SDKs
  • AI Answers (Enterprise Add-On): Available only as paid add-on to Enterprise plan—not included in Small Business tier
  • Overage Pricing: +15K views = $200/month, +30K views = $400/month (escalates quickly)
  • Automatic Tier Upgrades: Exceeding limits for 2 consecutive months triggers automatic upgrade and billing adjustment
  • Enterprise-Gated Features: AI Answers, Mobile SDKs, SAML SSO, white-labeling all require Enterprise plan
  • Average Enterprise Contract: ~$39,000 annually according to Vendr procurement data
  • 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
  • Dual Documentation Portals: docs.rag.progress.cloud (primary) + legacy docs.nuclia.dev (fragmentation concern during transition)
  • RAG Cookbook: Comprehensive downloadable guide for developers with implementation patterns and best practices
  • SDK Ecosystem: Python (~21K weekly downloads via pip install nuclia) + JavaScript/TypeScript (@nuclia/core on NPM)
  • REST API: Regional endpoints https://{region}.rag.progress.cloud/api/v1/ with complete programmatic control
  • Key Endpoints: /ask (generative answers), /find (semantic search), /upload (ingestion), /remi (quality evaluation)
  • 14-Day Free Trial: Hands-on evaluation platform without credit card requirement
  • Progress Enterprise Support: Backed by 2,000+ employee parent company infrastructure with dedicated account management
  • Open-Source Community: NucliaDB 710+ GitHub stars with AGPLv3 license transparency and community contributions
  • Integration Examples: WordPress, Strapi plugins, Pipedream official app, Zapier API-compatible, Chrome extension for web indexing
  • Progress Ecosystem: OpenEdge database connector, Sitefinity CMS integration ("first Generative CMS") for distribution advantages
  • 4.8/5 G2 Rating: 132 reviews with consistently high satisfaction scores
  • Ease of Use Praised: "Ease of use" mentioned 32 times in G2 reviews indicating intuitive platform
  • Help Center Documentation: Comprehensive guides and tutorials for platform features
  • Email and Chat Support: Standard support channels for all paid plans
  • Dedicated Support (Enterprise): Priority support with dedicated account team and faster response times
  • Pre-Built Templates: Common support scenario templates accelerating guide creation
  • Quick Onboarding: Users report creating guides in under 30 minutes with small learning curve
  • REST API Documentation: API reference for user provisioning, content management, and widget control
  • Mobile SDKs (Enterprise): iOS, Android, React Native, Flutter for native app integration
  • Limited Developer Resources: No Python/Node.js SDKs, GraphQL, OpenAPI specs, or API Explorer/sandbox
  • 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
  • Open-source resources: Python SDK (customgpt-client), Postman collections, GitHub integrations Open-Source SDK
  • Active community: User community plus 5,000+ app integrations through Zapier ecosystem
  • Regular updates: Platform stays current with ongoing GPT and retrieval improvements automatically
Limitations & Considerations
  • NO HIPAA Certification Documented: Healthcare organizations processing PHI must contact sales - major compliance gap vs competitors with documented HIPAA
  • NO Native Messaging Channels: No Slack, WhatsApp, Telegram, or Microsoft Teams integrations - requires custom API-based development
  • Documentation Fragmentation: Dual portals (docs.rag.progress.cloud + docs.nuclia.dev) during Progress acquisition transition may cause confusion
  • Recent Acquisition Risk: June 2025 Progress purchase means platform still maturing under new ownership with potential direction changes
  • Scalability Concerns: Multiple problems limit scalability - hard to scale nodes up/down, write operations affect concurrent search performance
  • NO Dropbox Integration: Missing Dropbox connector vs competitors - limits cloud storage sync options
  • NO Notion Integration: Missing Notion connector - gap for knowledge management workflows
  • NO YouTube Transcript Extraction: Not explicitly documented vs competitors with video indexing features
  • Token-Based Billing Complexity: $0.008/token beyond 10K/month requires careful usage forecasting vs predictable seat-based pricing
  • Missing Features: NO lead capture, NO human handoff/escalation workflows, NO proactive alerting (monitoring exists, alerting undocumented)
  • Learning Curve: 30+ RAG parameters and Prompt Lab may feel technical for non-developer teams despite no-code dashboard
  • Best For: Development teams and technical users - powerful for experts but may overwhelm business users wanting simple deployment
  • NOT a RAG-as-a-Service Platform: Fundamentally a knowledge base tool with embedded AI—not a flexible RAG backend
  • AI Answers Enterprise-Gated: Core AI capabilities require expensive Enterprise plan (~$39K/year)—not available on $249/month Small Business tier
  • Undisclosed AI Model: No transparency on LLM provider—users cannot select or customize models
  • Limited Data Source Flexibility: PDF, public web, Zendesk only—missing Google Drive, Dropbox, Notion, SharePoint, YouTube
  • No Automatic Content Syncing: Manual updates through visual editor—no real-time integration with external knowledge sources
  • Missing Consumer Messaging: No Slack, WhatsApp, Telegram, Microsoft Teams native integrations (confirmed by user reviews)
  • No Omnichannel Messaging: Primarily website embedding and help desk integration—limited multi-channel support
  • Cannot Edit on Mobile: Guide creation and editing restricted to desktop—mobile limitation for on-the-go teams
  • Angular Compatibility Issues: Reported "random" behavior with Angular framework dynamic code
  • No Real-Time Analytics: Flow reports update every 15 minutes—not true real-time monitoring
  • Limited Developer API: No Python/Node.js SDKs, GraphQL, Swagger specs, or API sandbox for testing
  • Overage Pricing Escalation: View limits can trigger expensive automatic upgrades after 2 consecutive months
  • Not Ideal For: Developers seeking pure RAG API, multi-tenant SaaS RAG backends, use cases needing model selection/fine-tuning, or flexible data source integration
  • 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
Core Knowledge Base Features
N/A
  • Interactive step-by-step guides with visual flow builder
  • Decision trees and branching logic
  • Checklists and task management
  • Contact forms and lead capture
  • Content versioning: Side-by-side comparison, instant restore
  • Multi-language support: Auto-translation on Enterprise plan
  • Knowledge bases: 3 on Small Business, unlimited on Enterprise
  • Guide views tracking: 400 (Free), 4,000 (Small Business), custom (Enterprise)
  • NPS surveys: All plans
  • CSAT and CES surveys: Enterprise only
N/A
A I Answers Feature ( Enterprise Only)
N/A
  • Note: Available only as paid Enterprise add-on - not included in Small Business plan
  • Generative AI responses grounded in Stonly guides, external websites, and selected PDFs
  • 20 AI Profiles per team: Define tone, boundaries, and behavior
  • 100 Custom Instructions per team: Detailed response rules
  • Guided AI Answers: Predefined responses for specific questions
  • Confidence-based fallback: Automatically switches to ML-powered search when AI confidence is low
  • 71% self-serve success rate achieved with AI Answers
  • Hallucination reduction: Knowledge-grounding approach vs generic chatbots
N/A

Ready to experience the CustomGPT difference?

Start Free Trial →

Final Thoughts

Final Verdict: Progress Agentic RAG vs Stonly

After analyzing features, pricing, performance, and user feedback, both Progress Agentic RAG and Stonly are capable platforms that serve different market segments and use cases effectively.

When to Choose Progress Agentic RAG

  • You value proprietary remi v2 model (30x faster inference) addresses hallucination problem with continuous quality monitoring - differentiated capability absent from most competitors
  • Open-source NucliaDB transparency (710+ GitHub stars) with managed infrastructure removes operational burden while maintaining technical visibility
  • Genuine no-code accessibility: business users (marketing, HR, legal, support) can deploy functional RAG pipelines in minutes via visual dashboard

Best For: Proprietary REMi v2 model (30x faster inference) addresses hallucination problem with continuous quality monitoring - differentiated capability absent from most competitors

When to Choose Stonly

  • You value exceptional ease of use - 4.8/5 g2 rating with intuitive visual editor praised in 32 reviews
  • Deep help desk integrations - bidirectional Zendesk, Salesforce, Freshdesk, ServiceNow connections
  • Strong compliance - SOC 2 Type 2, GDPR, HIPAA, ISO 27001, PCI, CSA Star Level 1

Best For: Exceptional ease of use - 4.8/5 G2 rating with intuitive visual editor praised in 32 reviews

Migration & Switching Considerations

Switching between Progress Agentic RAG and Stonly 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

Progress Agentic RAG starts at $700/month, while Stonly begins at $249/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

  1. Start with a free trial - Both platforms offer trial periods to test with your actual data
  2. Define success metrics - Response accuracy, latency, user satisfaction, cost per query
  3. Test with real use cases - Don't rely on generic demos; use your production data
  4. Evaluate total cost - Factor in implementation time, training, and ongoing maintenance
  5. Check vendor stability - Review roadmap transparency, update frequency, and support quality

For most organizations, the decision between Progress Agentic RAG and Stonly 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 12, 2025 | This comparison is regularly reviewed and updated to reflect the latest platform capabilities, pricing, and user feedback.

Ready to Get Started with CustomGPT?

Join thousands of businesses that trust CustomGPT for their AI needs. Choose the path that works best for you.

Why Choose CustomGPT?

97% Accuracy

Industry-leading benchmarks

5-Min Setup

Get started instantly

24/7 Support

Expert help when you need it

Enterprise Ready

Scale with confidence

Trusted by leading companies worldwide

Fortune 500Fortune 500Fortune 500Fortune 500Fortune 500Fortune 500

CustomGPT

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.

Get in touch
Contact Us

Join the Discussion

Loading comments...

Priyansh Khodiyar's avatar

Priyansh Khodiyar

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.

Watch: Understanding AI Tool Comparisons