{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_eddy-ai","slug":"eddy-ai","name":"Eddy AI","type":"product","url":"https://eddyai.com","page_url":"https://unfragile.ai/eddy-ai","categories":["chatbots-assistants"],"tags":[],"pricing":{"model":"freemium","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_eddy-ai__cap_0","uri":"capability://search.retrieval.faq.based.intent.matching.and.response.generation","name":"faq-based intent matching and response generation","description":"Eddy AI matches incoming customer queries against a knowledge base of FAQ entries using keyword and semantic similarity matching, then generates or retrieves pre-configured responses. The system uses pattern-based intent classification rather than deep NLP, making it fast but less capable of handling paraphrased or nuanced variations of common questions. Responses are templated and deterministic, reducing hallucination risk but limiting conversational flexibility.","intents":["I want to automatically answer the same 20 questions my customers ask repeatedly without hiring support staff","I need a chatbot that can handle basic product questions and shipping inquiries 24/7","I want to reduce support ticket volume by deflecting FAQ-style questions before they reach my team"],"best_for":["Small e-commerce businesses with well-defined, repetitive customer questions","Service businesses with stable FAQ content that rarely changes","Teams looking for high-accuracy responses over conversational naturalness"],"limitations":["Pattern-based matching struggles with paraphrased questions or contextual variations — accuracy drops significantly when customer phrasing deviates from training FAQ structure","No multi-turn context awareness — each query is evaluated independently, limiting ability to handle follow-up questions that reference previous exchanges","Cannot handle open-ended or subjective customer inquiries that fall outside the FAQ scope"],"requires":["Pre-built FAQ knowledge base with at least 10-20 Q&A pairs for meaningful coverage","Customer queries in text format (chat, email, or messaging platform)","Integration with at least one supported platform (Shopify, Slack, web widget, etc.)"],"input_types":["text (customer query)","structured FAQ data (question-answer pairs)"],"output_types":["text (templated response)","structured metadata (confidence score, matched FAQ ID)"],"categories":["search-retrieval","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_eddy-ai__cap_1","uri":"capability://planning.reasoning.lead.qualification.and.routing.to.human.agents","name":"lead qualification and routing to human agents","description":"Eddy AI identifies qualifying signals in customer conversations (e.g., purchase intent, budget mention, timeline) using rule-based classification and intent scoring, then routes qualified leads to human sales representatives or support queues. The system uses configurable decision trees and keyword triggers rather than probabilistic models, making routing deterministic but brittle when customer language deviates from expected patterns. Handoff includes conversation history and qualification metadata to contextualize the human agent's response.","intents":["I want to automatically qualify sales leads and only escalate high-intent prospects to my sales team","I need to route support tickets to the right department based on issue type without manual triage","I want to capture lead information (email, company, budget) before handing off to a sales rep"],"best_for":["Sales teams handling high inquiry volume who need to prioritize high-intent leads","Support organizations with multiple departments or skill-based routing requirements","Businesses with clear, rule-based qualification criteria (e.g., budget threshold, industry type)"],"limitations":["Rule-based routing is brittle — misses qualified leads when customer language doesn't match configured keywords or patterns","No probabilistic scoring — cannot rank leads by likelihood-to-convert; treats all qualified leads equally","Limited context awareness — cannot factor in customer history, previous interactions, or account-level signals when making routing decisions","Requires manual configuration of routing rules; no machine learning to adapt rules based on conversion outcomes"],"requires":["Configured routing rules and qualification criteria (manual setup required)","Integration with CRM or ticketing system to receive and store lead data","Human agent availability or queue system to receive routed conversations","Email or contact information capture mechanism (form or conversation extraction)"],"input_types":["text (customer conversation)","structured routing rules (JSON or UI-configured)"],"output_types":["structured lead data (name, email, company, qualification score)","routing decision (target queue, agent, or department)","conversation transcript with metadata"],"categories":["planning-reasoning","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_eddy-ai__cap_2","uri":"capability://tool.use.integration.multi.platform.conversation.aggregation.and.unified.inbox","name":"multi-platform conversation aggregation and unified inbox","description":"Eddy AI collects customer conversations from multiple channels (Shopify chat, Slack, web widget, email) and surfaces them in a unified inbox interface, preserving conversation history and metadata from each source. The system uses channel-specific adapters to normalize message formats and timestamps, then stores conversations in a centralized database indexed by customer identity. This allows support teams to view all customer interactions across channels without switching between tools, though the normalization process may lose channel-specific formatting or rich media.","intents":["I want to see all my customer conversations in one place instead of checking Shopify, email, and Slack separately","I need to track which channel a customer used to contact us and maintain conversation continuity across channels","I want my support team to respond to customers from a single dashboard without context-switching"],"best_for":["Small teams managing customer conversations across 2-4 channels","E-commerce businesses using Shopify who need to consolidate shop chat with other support channels","Businesses where support agents need a unified view of customer history"],"limitations":["Channel-specific features may be lost during normalization — rich media, formatting, or interactive elements from one platform may not render correctly in the unified inbox","No real-time sync guarantee — conversations may have slight delays (seconds to minutes) before appearing in the unified view, especially for high-volume channels","Limited channel coverage — only supports a fixed set of integrations (Shopify, Slack, web widget, email); custom channels or newer platforms require development","No channel-specific routing rules — cannot automatically assign conversations to agents based on the channel they came from"],"requires":["Active accounts on at least one supported platform (Shopify, Slack, email, web widget)","API credentials or OAuth tokens for each connected platform","Support team members with access to the unified inbox dashboard","Stable internet connection for real-time conversation sync"],"input_types":["messages from multiple channels (chat, email, Slack, Shopify)","customer identity data (email, phone, Shopify customer ID)"],"output_types":["unified conversation thread (normalized text, timestamps, channel metadata)","customer profile (aggregated from all channels)","conversation list with filtering and search"],"categories":["tool-use-integration","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_eddy-ai__cap_3","uri":"capability://tool.use.integration.shopify.integration.with.product.catalog.awareness","name":"shopify integration with product catalog awareness","description":"Eddy AI connects to Shopify's API to access product catalog data, customer purchase history, and order information, enabling the chatbot to answer product-specific questions and provide personalized recommendations based on browsing or purchase context. The integration syncs product metadata (name, description, price, inventory) and customer data (order history, cart contents) into Eddy's knowledge base, allowing the bot to reference real-time product information and customer context when responding to queries. This reduces the need for manual FAQ updates when products change.","intents":["I want my chatbot to answer questions about specific products using real product data from my Shopify store","I need the bot to check inventory and tell customers if a product is in stock before they ask","I want to recommend products to customers based on their browsing history or previous purchases"],"best_for":["Shopify store owners selling physical or digital products with frequently changing inventory","E-commerce businesses where product details (price, availability, specs) change regularly","Stores with large product catalogs where manual FAQ maintenance is impractical"],"limitations":["Sync latency — product changes in Shopify may take minutes to hours to reflect in the chatbot, causing stale information during flash sales or inventory updates","Limited to Shopify ecosystem — cannot integrate with other e-commerce platforms (WooCommerce, Magento, custom storefronts) without custom development","No real-time inventory checking — the bot references cached inventory data rather than querying live stock levels, potentially giving incorrect availability information during high-traffic periods","Product recommendations are rule-based (e.g., 'frequently bought together') rather than ML-driven, limiting personalization quality"],"requires":["Active Shopify store with API access enabled","Shopify API credentials (OAuth token or API key)","Product catalog with at least basic metadata (name, description, price)","Eddy AI integration configured in Shopify app store or via manual API setup"],"input_types":["Shopify product catalog (via API)","Customer purchase history (via Shopify API)","Customer query (text)"],"output_types":["product information (name, price, description, availability)","personalized recommendations (product list with context)","order status or customer history summary"],"categories":["tool-use-integration","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_eddy-ai__cap_4","uri":"capability://tool.use.integration.slack.channel.integration.with.conversation.threading","name":"slack channel integration with conversation threading","description":"Eddy AI connects to Slack workspaces to receive customer inquiries posted in designated channels, respond directly in Slack threads, and escalate complex issues to human agents. The integration uses Slack's Events API to listen for messages, maintains conversation context within Slack threads, and allows agents to respond from Slack without leaving the platform. Responses are posted as bot messages with metadata tags indicating confidence level or escalation status, enabling teams to manage customer interactions entirely within Slack.","intents":["I want to use Slack as my customer support channel and have the bot handle routine questions automatically","I need my support team to see bot responses and escalations in Slack without switching to another tool","I want to track which questions the bot handled vs. which required human intervention, all within Slack"],"best_for":["Teams already using Slack as their primary communication hub who want to extend it to customer support","Internal support teams managing customer inquiries through Slack channels","Businesses with small support teams who prefer not to adopt a separate ticketing system"],"limitations":["Slack is not a ticketing system — no built-in SLA tracking, assignment workflows, or escalation queues; teams must use Slack's threading and emoji reactions as workarounds","Conversation history is limited by Slack's message retention policy (free tier: 90 days; paid: unlimited); older conversations are not accessible to the bot","No customer authentication — Slack channels are internal; external customers cannot directly message the bot through Slack without a separate integration layer","Limited rich media support — Slack's message formatting constraints may prevent the bot from displaying complex product information or interactive elements"],"requires":["Active Slack workspace with admin permissions to install apps","Slack app installed and configured with bot token and event subscriptions","Designated Slack channel(s) for customer inquiries","Support team members with Slack access"],"input_types":["Slack messages (text, emoji reactions)","Slack user metadata (name, email, profile)"],"output_types":["Slack bot messages (text, formatted blocks, metadata tags)","thread replies with escalation indicators","conversation summaries for human agents"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_eddy-ai__cap_5","uri":"capability://planning.reasoning.configurable.conversation.flows.and.branching.logic","name":"configurable conversation flows and branching logic","description":"Eddy AI allows non-technical users to design multi-turn conversation flows using a visual builder or configuration interface, defining branching logic based on customer responses, keywords, or intent classifications. The system supports conditional branches (if-then rules), loops, and handoff triggers, enabling teams to create guided conversations that collect information progressively without requiring code. Flows are stored as configuration objects and executed by a state machine that tracks conversation state and applies rules at each step.","intents":["I want to create a conversation flow that asks customers about their issue, then routes them to the right department","I need to collect customer information (name, email, issue description) through a guided conversation before escalating to support","I want to build a sales qualification flow that asks about budget and timeline without writing code"],"best_for":["Non-technical support managers who need to update conversation flows without developer involvement","Businesses with complex qualification or triage workflows that require branching logic","Teams that need to iterate on conversation flows frequently based on customer feedback"],"limitations":["Visual builder may be limited in expressiveness — complex logic (nested conditions, dynamic variable substitution, API-based branching) may require manual JSON editing or custom development","No A/B testing framework — cannot easily test different conversation flows against each other to optimize conversion or satisfaction metrics","State management is conversation-scoped — no persistent state across multiple conversations or sessions, limiting ability to build long-term customer journeys","Branching logic is rule-based, not probabilistic — cannot weight branches by likelihood or learn from conversation outcomes to optimize routing"],"requires":["Access to Eddy AI's flow builder (web UI or API)","Understanding of conversation design principles (question phrasing, branching logic)","Test environment to validate flows before deploying to production","Optional: JSON or configuration file format knowledge for advanced customization"],"input_types":["conversation flow definition (visual or JSON)","customer responses (text, button clicks, form submissions)","conditional rules (if-then logic)"],"output_types":["conversation state (current step, collected variables)","bot response (text, buttons, form fields)","routing decision (escalation, handoff, loop)"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_eddy-ai__cap_6","uri":"capability://data.processing.analysis.conversation.analytics.and.performance.reporting","name":"conversation analytics and performance reporting","description":"Eddy AI tracks metrics on bot conversations (volume, resolution rate, escalation rate, average response time) and surfaces them in a dashboard with filtering by time period, channel, or conversation type. The system logs conversation transcripts and metadata (intent, confidence score, customer satisfaction if available) to enable post-hoc analysis and performance optimization. However, analytics are limited to basic metrics; the platform lacks advanced insights like sentiment analysis, topic clustering, or predictive indicators of customer churn.","intents":["I want to see how many customer questions my bot is handling vs. escalating to humans","I need to identify which types of questions the bot struggles with so I can improve the FAQ","I want to track bot performance over time to justify the investment to my manager"],"best_for":["Support managers who need basic metrics to track bot ROI and identify improvement areas","Teams with simple, FAQ-based support workflows where standard metrics are sufficient","Businesses that don't require deep conversation insights or predictive analytics"],"limitations":["Limited metric depth — dashboard shows volume, resolution rate, and escalation rate, but lacks sentiment analysis, topic clustering, or customer satisfaction scoring","No predictive analytics — cannot identify at-risk customers or predict which conversations will require escalation before they happen","Conversation export is basic — transcripts are available but lack structured analysis or tagging; teams must manually review conversations to identify patterns","No A/B testing framework — cannot compare performance across different conversation flows or FAQ versions","Analytics are conversation-scoped — no account-level or customer lifetime metrics to understand long-term impact"],"requires":["Active conversations flowing through Eddy AI (minimum 10-20 conversations for meaningful metrics)","Access to the analytics dashboard (typically included in paid plans)","Optional: CSV export or API access for custom analysis"],"input_types":["conversation transcripts (text, metadata)","bot responses and escalations (structured logs)","customer satisfaction feedback (if collected)"],"output_types":["dashboard metrics (volume, resolution rate, escalation rate, response time)","conversation transcripts with metadata","time-series charts and trend analysis","CSV export for external analysis"],"categories":["data-processing-analysis","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_eddy-ai__cap_7","uri":"capability://tool.use.integration.web.widget.deployment.with.customizable.appearance","name":"web widget deployment with customizable appearance","description":"Eddy AI provides an embeddable web widget (JavaScript snippet) that can be deployed on any website to initiate customer conversations. The widget supports customization of appearance (colors, logo, position, greeting message) through a configuration UI or code, and uses a lightweight iframe to isolate the chat interface from the host page's styling. The widget persists conversation state in browser local storage, allowing customers to resume conversations across page navigations without re-authentication.","intents":["I want to add a chat widget to my website so customers can ask questions without leaving the page","I need the widget to match my brand colors and logo so it looks native to my site","I want customers to be able to close the chat and resume it later without losing context"],"best_for":["Website owners who want to add customer support without building a custom chat interface","Businesses with simple branding requirements who don't need extensive customization","Teams that want to deploy support quickly without backend infrastructure"],"limitations":["Limited customization — appearance options are constrained to predefined themes and color schemes; custom layouts or advanced styling require CSS overrides or custom development","No persistent authentication — widget uses browser local storage, so conversation state is lost if the customer clears cookies or uses a different device/browser","Performance impact — the widget adds JavaScript and network requests to the host page, potentially increasing page load time by 200-500ms depending on network conditions","No analytics integration — widget interactions (open, close, message sent) are not automatically tracked in Google Analytics or other third-party tools without custom instrumentation","Mobile responsiveness is basic — widget layout may not adapt well to very small screens or landscape orientation"],"requires":["Website with ability to add custom JavaScript (HTML access or tag manager)","Eddy AI account with web widget enabled","Widget configuration (colors, greeting message, position)","Optional: custom CSS or JavaScript for advanced styling"],"input_types":["customer messages (text, emoji)","widget configuration (JSON or UI)","customer browser metadata (user agent, referrer)"],"output_types":["chat interface (HTML/CSS/JavaScript)","conversation transcript (stored in Eddy backend)","customer session data (browser local storage)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_eddy-ai__cap_8","uri":"capability://automation.workflow.escalation.to.human.agents.with.context.preservation","name":"escalation to human agents with context preservation","description":"When a customer query falls outside the bot's FAQ scope or explicitly requests human assistance, Eddy AI transfers the conversation to a human agent, including the full conversation history, collected customer information, and bot confidence scores. The escalation process uses a queue or assignment system to route conversations to available agents, with optional skill-based routing if configured. The agent receives a summary of the conversation and any qualification data collected by the bot, reducing context-switching and enabling faster resolution.","intents":["I want the bot to automatically escalate complex questions to my support team with full conversation context","I need to ensure customers don't have to repeat themselves when they're transferred from the bot to a human","I want to track which conversations required human intervention so I can improve the bot's FAQ"],"best_for":["Support teams using Eddy AI as a first-line deflection tool before human escalation","Businesses with clear escalation criteria (e.g., 'if bot confidence < 50%, escalate')","Teams that want to reduce customer frustration by preserving context during handoffs"],"limitations":["No intelligent escalation prediction — escalation is rule-based (e.g., 'if no FAQ match, escalate') rather than learning from past escalations to predict which conversations will require human help","Queue management is basic — no SLA tracking, priority queuing, or automatic timeout handling; teams must manage agent availability separately","No warm handoff — the bot cannot consult with a human agent before escalating; it's a cold transfer that may result in duplicate questions","Agent interface is limited — agents view escalated conversations in the unified inbox but lack specialized tools for complex issue resolution (e.g., screen sharing, co-browsing)","No escalation feedback loop — agents cannot easily mark escalations as 'could have been handled by bot' to improve the FAQ"],"requires":["Human agents available to receive escalated conversations (via unified inbox or integrated ticketing system)","Configured escalation rules (e.g., confidence threshold, keyword triggers)","Optional: CRM or ticketing system integration to create tickets from escalations","Optional: skill-based routing configuration if assigning to specialized agents"],"input_types":["conversation transcript (text, metadata)","customer information (name, email, account data)","escalation trigger (rule match, explicit request, timeout)"],"output_types":["escalation ticket or queue entry","agent notification (email, in-app alert)","conversation summary with context","escalation metadata (reason, bot confidence, customer sentiment)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_eddy-ai__cap_9","uri":"capability://tool.use.integration.email.integration.for.asynchronous.customer.support","name":"email integration for asynchronous customer support","description":"Eddy AI can receive customer inquiries via email, process them through the same FAQ matching and intent classification logic as chat conversations, and send responses back via email. The integration uses email parsing to extract the customer message and metadata (sender, subject), matches it against the FAQ knowledge base, and generates or retrieves a response. If escalation is needed, the email is converted to a support ticket and routed to a human agent. This enables teams to handle email support without manually copying conversations into the chat system.","intents":["I want to handle customer emails automatically using the same FAQ knowledge base as my chat bot","I need to track which emails the bot handled vs. which required human escalation","I want to reduce email support volume by automatically responding to common questions"],"best_for":["Businesses receiving a mix of chat and email inquiries who want unified handling","Teams with high email volume where FAQ-based responses can deflect significant traffic","Support organizations that prefer email as a communication channel for certain customer segments"],"limitations":["Email parsing is fragile — forwarded emails, quoted text, and complex formatting may confuse the parser, leading to incorrect intent classification or escalation","No threading awareness — email conversations with multiple back-and-forths may be treated as separate inquiries if the parser fails to identify the conversation thread","Response latency — email responses are asynchronous and may take minutes to hours to send, whereas chat responses are immediate; this may frustrate customers expecting quick replies","Limited rich media support — email responses are plain text or basic HTML; the bot cannot send interactive elements (buttons, forms) that are available in chat","Spam and false positives — the bot may respond to marketing emails, notifications, or spam if the email filtering is not configured correctly"],"requires":["Email account (Gmail, Outlook, custom domain) with IMAP or API access","Email forwarding or integration configured to route customer emails to Eddy AI","Email parsing rules configured to extract customer message and metadata","Optional: email template configuration for bot responses"],"input_types":["email message (text, HTML, attachments)","email metadata (sender, subject, timestamp, thread ID)"],"output_types":["email response (plain text or HTML)","escalation ticket (if needed)","conversation transcript (stored in Eddy backend)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":41,"verified":false,"data_access_risk":"high","permissions":["Pre-built FAQ knowledge base with at least 10-20 Q&A pairs for meaningful coverage","Customer queries in text format (chat, email, or messaging platform)","Integration with at least one supported platform (Shopify, Slack, web widget, etc.)","Configured routing rules and qualification criteria (manual setup required)","Integration with CRM or ticketing system to receive and store lead data","Human agent availability or queue system to receive routed conversations","Email or contact information capture mechanism (form or conversation extraction)","Active accounts on at least one supported platform (Shopify, Slack, email, web widget)","API credentials or OAuth tokens for each connected platform","Support team members with access to the unified inbox dashboard"],"failure_modes":["Pattern-based matching struggles with paraphrased questions or contextual variations — accuracy drops significantly when customer phrasing deviates from training FAQ structure","No multi-turn context awareness — each query is evaluated independently, limiting ability to handle follow-up questions that reference previous exchanges","Cannot handle open-ended or subjective customer inquiries that fall outside the FAQ scope","Rule-based routing is brittle — misses qualified leads when customer language doesn't match configured keywords or patterns","No probabilistic scoring — cannot rank leads by likelihood-to-convert; treats all qualified leads equally","Limited context awareness — cannot factor in customer history, previous interactions, or account-level signals when making routing decisions","Requires manual configuration of routing rules; no machine learning to adapt rules based on conversion outcomes","Channel-specific features may be lost during normalization — rich media, formatting, or interactive elements from one platform may not render correctly in the unified inbox","No real-time sync guarantee — conversations may have slight delays (seconds to minutes) before appearing in the unified view, especially for high-volume channels","Limited channel coverage — only supports a fixed set of integrations (Shopify, Slack, web widget, email); custom channels or newer platforms require development","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.31666666666666665,"quality":0.72,"ecosystem":0.15000000000000002,"match_graph":0.25,"freshness":0.9,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.35,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:30.283Z","last_scraped_at":"2026-04-05T13:23:42.561Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=eddy-ai","compare_url":"https://unfragile.ai/compare?artifact=eddy-ai"}},"signature":"WrNJ5dfnoDA4WPxzSoKXwUZpktb6preHBHjOhEbfzAd0drgQwxuGjhNwKYGRF8Knuc0Jb+300AsuRRULeETXDg==","signedAt":"2026-06-16T23:44:45.895Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/eddy-ai","artifact":"https://unfragile.ai/eddy-ai","verify":"https://unfragile.ai/api/v1/verify?slug=eddy-ai","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}