{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_mychatbots-ai","slug":"mychatbots-ai","name":"MyChatbots.AI","type":"product","url":"https://mychatbots.ai","page_url":"https://unfragile.ai/mychatbots-ai","categories":["chatbots-assistants","model-training"],"tags":[],"pricing":{"model":"paid","free":false,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_mychatbots-ai__cap_0","uri":"capability://planning.reasoning.no.code.chatbot.builder.with.drag.and.drop.conversation.flow.design","name":"no-code chatbot builder with drag-and-drop conversation flow design","description":"Provides a visual interface for constructing multi-turn conversation flows without writing code, using a node-based or block-based graph editor where users define intents, responses, and conditional branching logic. The builder likely compiles these visual flows into an internal state machine or decision tree that the chatbot engine executes at runtime, eliminating the need for developers to hand-code dialogue logic or NLU pipelines.","intents":["I want to build a customer support chatbot without hiring a developer","I need to quickly prototype different conversation flows and test them","I want to add conditional logic (if customer says X, respond with Y) without touching code"],"best_for":["non-technical founders and small business owners building their first chatbot","customer support teams managing chatbot updates without engineering involvement","agencies rapidly prototyping chatbot solutions for multiple clients"],"limitations":["Visual builders typically lack expressiveness for complex business logic — advanced conditional flows or dynamic data transformations may require workarounds or custom code","No-code abstractions often hide performance tuning options, making it difficult to optimize response latency for high-traffic scenarios","Drag-and-drop interfaces scale poorly for very large conversation trees (100+ intents), becoming unwieldy to navigate and maintain"],"requires":["Web browser with modern JavaScript support (Chrome, Firefox, Safari, Edge)","Account creation on MyChatbots.AI platform","No programming knowledge required"],"input_types":["text (user intent descriptions, response templates)","structured data (intent-response mappings, conditional rules)"],"output_types":["executable chatbot flow (compiled state machine or dialogue graph)","embeddable chatbot widget code"],"categories":["planning-reasoning","no-code-automation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mychatbots-ai__cap_1","uri":"capability://data.processing.analysis.custom.model.training.on.business.specific.data","name":"custom model training on business-specific data","description":"Allows users to upload proprietary datasets (FAQs, past conversations, product documentation) to fine-tune the underlying language model or train intent classifiers specific to their domain, improving response relevance and accuracy without retraining from scratch. The platform likely implements transfer learning or few-shot adaptation techniques to quickly specialize a base model on customer-provided examples, reducing training time and data requirements compared to full model retraining.","intents":["I want my chatbot to understand industry-specific terminology and jargon","I need to train the bot on my company's product documentation and FAQs","I want to improve response accuracy by feeding it examples of good and bad responses"],"best_for":["businesses in specialized verticals (healthcare, legal, finance) with domain-specific language","companies with large existing knowledge bases wanting to leverage them for chatbot training","teams iterating on chatbot quality and needing rapid feedback loops on training data impact"],"limitations":["Training on small datasets (< 100 examples) may lead to overfitting or poor generalization to out-of-domain queries","No visibility into which training examples influenced specific predictions, making debugging incorrect responses difficult","Training latency and cost scale with dataset size; very large datasets (10K+ examples) may incur significant processing time or fees","Platform likely does not support custom model architectures or hyperparameter tuning, limiting optimization for specific use cases"],"requires":["Structured training data in supported formats (CSV, JSON, or plain text)","Minimum dataset size (likely 10-50 examples per intent, platform-dependent)","API key or authentication token for training job submission"],"input_types":["CSV or JSON files with intent-response pairs","Plain text documents (FAQs, product docs)","Conversation transcripts or chat logs"],"output_types":["fine-tuned model checkpoint or weights","updated chatbot instance with improved intent classification","training metrics and accuracy reports"],"categories":["data-processing-analysis","model-training"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mychatbots-ai__cap_10","uri":"capability://text.generation.language.multi.language.support.and.localization","name":"multi-language support and localization","description":"Enables the chatbot to understand and respond in multiple languages, using either language detection to automatically route messages to language-specific models or explicit language selection by users. The platform likely maintains separate intent classifiers and response templates per language, or uses a multilingual model (mBERT, XLM-RoBERTa) that handles multiple languages in a single model, with optional translation pipelines for knowledge base documents.","intents":["I want my chatbot to serve customers in multiple languages without building separate bots","I need the bot to automatically detect the customer's language and respond appropriately","I want to localize responses for different regions or languages"],"best_for":["global businesses serving customers in multiple countries and languages","e-commerce companies with international customer bases","customer support teams managing multilingual support without separate teams per language"],"limitations":["Multilingual models often have lower accuracy per language compared to monolingual models; language-specific nuances may be lost","Language detection can fail on code-mixed text (e.g., 'Hola, what's the status of my order?'); the bot may misclassify the intended language","Translation of knowledge base documents may introduce errors or loss of meaning; human review is recommended for critical content","Training data requirements scale with number of languages; supporting 10+ languages may require significantly more training data per language"],"requires":["Intent definitions and response templates for each supported language","Training data in each language (or translation of existing training data)","Optional: language detection model or explicit language selection UI"],"input_types":["user message in any supported language","language code or auto-detected language","multilingual training data or translations"],"output_types":["detected language code","response in the user's language","confidence score for language detection"],"categories":["text-generation-language","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mychatbots-ai__cap_11","uri":"capability://data.processing.analysis.sentiment.analysis.and.conversation.quality.monitoring","name":"sentiment analysis and conversation quality monitoring","description":"Analyzes user messages and conversation outcomes to detect sentiment (positive, negative, neutral) and identify conversations with poor outcomes (low satisfaction, escalations, repeated questions), enabling proactive intervention or quality improvement. The platform likely uses a sentiment classifier (rule-based or neural) to score each user message and aggregates sentiment over the conversation to identify dissatisfied customers, with optional integration to alerting systems for real-time notifications.","intents":["I want to identify conversations where the customer is frustrated or dissatisfied","I need to track conversation quality and identify patterns in failed interactions","I want to be alerted when a conversation is going poorly so I can intervene"],"best_for":["customer support teams wanting to proactively identify and resolve customer dissatisfaction","businesses tracking customer satisfaction metrics and NPS","companies using chatbot quality as a KPI and needing real-time monitoring"],"limitations":["Sentiment analysis accuracy is limited on sarcasm, negation, and context-dependent language; the classifier may misinterpret tone","Sentiment scores are aggregated at the conversation level, losing granularity about which specific bot responses caused dissatisfaction","No causal analysis; the system can identify poor conversations but not explain why they went poorly or what the bot should have done differently","Alerts may be noisy if sentiment thresholds are not carefully tuned; false positives can lead to alert fatigue"],"requires":["Conversation logs with user messages and bot responses","Optional: user satisfaction ratings or feedback for training sentiment classifier","Alerting system or integration (email, Slack, etc.) for notifications"],"input_types":["user message text","conversation history","optional: explicit user satisfaction rating"],"output_types":["sentiment score per message (positive, negative, neutral)","overall conversation sentiment","quality flags or alerts for poor conversations"],"categories":["data-processing-analysis","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mychatbots-ai__cap_2","uri":"capability://tool.use.integration.multi.channel.chatbot.embedding.and.deployment","name":"multi-channel chatbot embedding and deployment","description":"Provides pre-built integrations and embedding options to deploy trained chatbots across multiple communication channels (websites, Facebook Messenger, WhatsApp, Slack, etc.) without requiring separate API integrations for each platform. The platform likely maintains a unified chatbot backend that abstracts channel-specific message formats and protocols, translating between the chatbot's internal message representation and each channel's API requirements.","intents":["I want to embed a chatbot on my website without writing custom code","I need my chatbot to handle customer inquiries across multiple messaging platforms","I want to manage all chatbot conversations from a single dashboard regardless of channel"],"best_for":["small to mid-sized businesses managing customer support across multiple channels","e-commerce companies wanting to add chat support to their website and social media","customer service teams seeking a unified inbox for all chatbot interactions"],"limitations":["Channel-specific features (rich media, interactive buttons, carousels) may not be fully supported across all platforms, requiring fallback to plain text","Message routing and context preservation across channels can be lossy — a conversation started on web may not seamlessly continue on WhatsApp","Rate limiting and quota management per channel are platform-dependent; high-volume scenarios may hit channel-specific API limits","Webhook-based integrations introduce latency and potential message loss if the platform's integration layer experiences downtime"],"requires":["Active accounts or API credentials for target messaging platforms (Facebook, WhatsApp, Slack, etc.)","Website domain ownership or admin access for web embedding","Platform API keys or OAuth tokens for channel authentication"],"input_types":["chatbot instance ID or deployment configuration","channel-specific credentials (API keys, webhook URLs)","custom styling or branding parameters for web widget"],"output_types":["embeddable JavaScript widget for websites","webhook URLs for messaging platform integrations","unified conversation logs and analytics across channels"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mychatbots-ai__cap_3","uri":"capability://text.generation.language.intent.recognition.and.response.matching","name":"intent recognition and response matching","description":"Automatically classifies incoming user messages into predefined intents and retrieves or generates appropriate responses, using either rule-based pattern matching, traditional NLU models (Naive Bayes, SVM), or neural intent classifiers (transformers, BERT-based models). The platform likely maintains an intent registry built during the no-code builder phase and uses semantic similarity or keyword matching to map user inputs to the closest intent, then retrieves the corresponding response template or triggers a custom action.","intents":["I want the chatbot to understand what the customer is asking and respond appropriately","I need the bot to handle variations of the same question (e.g., 'What's your hours?' vs 'When are you open?')","I want to route complex queries to human agents when the bot's confidence is low"],"best_for":["businesses with well-defined, repetitive customer inquiries (FAQs, account info, order status)","customer support teams wanting to automate 60-80% of routine questions","companies with limited training data or domain-specific language requiring simple pattern matching"],"limitations":["Intent classification accuracy degrades on out-of-domain or adversarial inputs; the bot may confidently misclassify ambiguous queries","Requires explicit intent definition during training — the system cannot discover new intents from user interactions without manual retraining","Semantic similarity-based matching may fail on typos, slang, or colloquial language not present in training data","No built-in confidence thresholding or fallback mechanism; low-confidence predictions may still trigger responses instead of escalating to human agents"],"requires":["Predefined intent list with at least 2-5 example utterances per intent","Response templates or action mappings for each intent","Optional: training data in CSV or JSON format to improve classification accuracy"],"input_types":["user message (text)","intent definitions with example utterances","response templates or action configurations"],"output_types":["classified intent with confidence score","matched response text or action trigger","fallback or escalation signal if confidence is below threshold"],"categories":["text-generation-language","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mychatbots-ai__cap_4","uri":"capability://memory.knowledge.conversation.context.and.session.management","name":"conversation context and session management","description":"Maintains conversation state across multiple turns, tracking user identity, conversation history, and context variables (e.g., customer name, order ID, previous questions) to enable coherent multi-turn dialogues. The platform likely stores conversation sessions in a backend database or cache (Redis, DynamoDB) keyed by user ID or session token, retrieving relevant context on each message to inform response generation and avoid repetitive questions.","intents":["I want the chatbot to remember what the customer asked earlier in the conversation","I need to personalize responses using customer information (name, account status, order history)","I want to track conversation state to handle complex workflows (e.g., multi-step order placement)"],"best_for":["customer support scenarios requiring multi-turn problem resolution","e-commerce chatbots guiding users through product selection or checkout","businesses needing to maintain context across channel switches (web to WhatsApp)"],"limitations":["Context window is limited by the underlying LLM or storage backend; very long conversations (100+ turns) may exceed token limits or incur high retrieval costs","Session data must be explicitly managed and cleaned up; orphaned sessions can accumulate and consume storage","Cross-channel context preservation is lossy — a conversation started on web may not have full history available on WhatsApp due to platform limitations","No built-in privacy controls; sensitive customer data (PII, payment info) stored in conversation context requires explicit encryption and compliance measures"],"requires":["Backend storage system (database or cache) for session data","User identification mechanism (login, anonymous session token, phone number)","Session timeout configuration (e.g., 30 minutes of inactivity)"],"input_types":["user message with session ID or user identifier","context variables (customer name, order ID, etc.)","conversation history (previous turns)"],"output_types":["updated session state with new context variables","response informed by conversation history","session metadata (start time, turn count, last activity)"],"categories":["memory-knowledge","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mychatbots-ai__cap_5","uri":"capability://data.processing.analysis.analytics.and.conversation.insights.dashboard","name":"analytics and conversation insights dashboard","description":"Provides a dashboard for monitoring chatbot performance metrics (conversation volume, intent distribution, user satisfaction, resolution rates) and analyzing conversation patterns to identify improvement opportunities. The platform likely aggregates conversation logs, computes metrics in real-time or batch, and visualizes trends over time, enabling product managers and support teams to understand chatbot effectiveness and prioritize training data improvements.","intents":["I want to see how many conversations my chatbot is handling and what topics come up most","I need to identify which intents have low resolution rates and require better training","I want to track customer satisfaction and identify conversations that should have been escalated to humans"],"best_for":["customer support managers optimizing chatbot performance and ROI","product teams using chatbot analytics to inform feature development","businesses tracking KPIs like resolution rate, average response time, and customer satisfaction"],"limitations":["Analytics are only as good as the underlying data — if conversations are not properly logged or classified, metrics will be inaccurate","Real-time dashboards may have latency (5-15 minutes) due to data aggregation and processing pipelines","Segmentation and filtering options may be limited; advanced cohort analysis or custom metrics may require exporting raw data","No built-in A/B testing framework; comparing performance across different chatbot versions requires manual setup"],"requires":["Active chatbot deployment with conversation logging enabled","Dashboard access credentials (login to MyChatbots.AI platform)","Minimum conversation volume (likely 10-100 conversations) for meaningful metrics"],"input_types":["conversation logs (user messages, bot responses, intents, timestamps)","user feedback or satisfaction ratings (optional)","custom event tracking (e.g., escalations, conversions)"],"output_types":["dashboard visualizations (charts, graphs, tables)","performance metrics (resolution rate, avg response time, intent distribution)","exportable reports (CSV, PDF)"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mychatbots-ai__cap_6","uri":"capability://automation.workflow.human.handoff.and.escalation.workflow","name":"human handoff and escalation workflow","description":"Enables seamless escalation of conversations from the chatbot to human agents when the bot cannot resolve a query or confidence is low, maintaining conversation context and history during the handoff. The platform likely implements a queue-based escalation system where unresolved conversations are routed to available agents, with optional integration to ticketing systems or live chat platforms to manage the human-handled portion of the conversation.","intents":["I want the chatbot to escalate complex queries to human agents without losing context","I need to route conversations to specific agent teams based on topic or customer tier","I want to track escalations and measure how many conversations require human intervention"],"best_for":["customer support teams using chatbots to handle routine inquiries while maintaining human support for complex issues","businesses wanting to measure chatbot effectiveness by tracking escalation rates","companies with tiered support (e.g., VIP customers always get human agents)"],"limitations":["Escalation latency depends on agent availability; customers may experience wait times if no agents are available","Context preservation during handoff is imperfect — agents may need to re-read conversation history or ask clarifying questions","No built-in skill-based routing; escalations may go to the first available agent rather than the most qualified one","Integration with external ticketing systems (Zendesk, Jira) may require custom configuration or API keys"],"requires":["Human agent availability or integration with live chat/ticketing platform","Queue management system for routing escalated conversations","Optional: integration credentials for external support tools (Zendesk, Intercom, etc.)"],"input_types":["escalation trigger (low confidence, explicit user request, intent match)","conversation context and history","agent availability and skill tags"],"output_types":["escalation event logged to analytics","conversation transferred to agent queue","ticket or conversation record created in external system"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mychatbots-ai__cap_7","uri":"capability://text.generation.language.response.template.management.and.personalization","name":"response template management and personalization","description":"Allows users to define and manage response templates with variable placeholders (e.g., {{customer_name}}, {{order_id}}) that are dynamically filled at runtime using conversation context or external data sources. The platform likely implements a template engine (Jinja2, Handlebars, or custom) that supports conditional logic and loops, enabling personalized responses without requiring code changes or retraining.","intents":["I want to personalize chatbot responses with customer names and account information","I need to dynamically insert product details or pricing into responses","I want to create response variants based on customer attributes (VIP status, language, etc.)"],"best_for":["e-commerce businesses personalizing product recommendations and pricing","customer support teams using customer data to provide personalized assistance","businesses managing multiple response variants for A/B testing or localization"],"limitations":["Template syntax may be limited; complex logic (nested conditionals, custom functions) may require workarounds or custom code","Variable resolution depends on availability of context data; missing variables may result in broken or incomplete responses","No built-in validation; typos in variable names or template syntax may not be caught until runtime","Performance overhead of template rendering scales with template complexity; very complex templates may add latency to response generation"],"requires":["Response templates defined in the platform's template format","Context variables available at runtime (from conversation state, user profile, or external APIs)","Optional: integration with external data sources (CRM, product database) for variable resolution"],"input_types":["response template text with variable placeholders","context variables (customer name, order ID, product details)","conditional logic rules"],"output_types":["rendered response text with variables substituted","personalized message ready for delivery to user"],"categories":["text-generation-language","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mychatbots-ai__cap_8","uri":"capability://tool.use.integration.api.based.chatbot.interaction.and.integration","name":"api-based chatbot interaction and integration","description":"Exposes REST or GraphQL APIs allowing external applications to send messages to the chatbot and receive responses programmatically, enabling integration with custom applications, third-party services, or backend systems. The platform likely maintains API endpoints for message submission, conversation retrieval, and session management, with authentication via API keys or OAuth tokens, allowing developers to embed chatbot functionality in non-standard interfaces or automate chatbot interactions.","intents":["I want to integrate the chatbot into my custom application or website","I need to programmatically send messages to the chatbot and process responses","I want to build a custom UI for the chatbot instead of using the default widget"],"best_for":["developers building custom applications that need chatbot functionality","teams integrating chatbots with proprietary backend systems or workflows","companies building mobile apps or custom interfaces requiring chatbot APIs"],"limitations":["API rate limiting may restrict high-volume scenarios; burst traffic could hit rate limits and require backoff logic","API latency adds overhead compared to local chatbot execution; network round-trips introduce 50-500ms latency per request","Authentication and API key management add complexity; compromised keys could expose chatbot to unauthorized access","API documentation and SDKs may be incomplete or outdated; developers may need to reverse-engineer API behavior"],"requires":["API key or OAuth credentials for authentication","HTTP client library (curl, requests, axios, etc.)","Knowledge of REST or GraphQL API design","Network connectivity to MyChatbots.AI API endpoints"],"input_types":["user message (text)","session ID or user identifier","optional: context variables or metadata"],"output_types":["chatbot response (text)","intent classification and confidence score","conversation metadata (session ID, turn count)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mychatbots-ai__cap_9","uri":"capability://memory.knowledge.knowledge.base.integration.and.document.indexing","name":"knowledge base integration and document indexing","description":"Allows users to upload or link external knowledge sources (PDFs, web pages, documentation) that the chatbot can reference when generating responses, using semantic search or keyword matching to retrieve relevant documents. The platform likely implements a document ingestion pipeline that extracts text, creates embeddings, and indexes documents in a vector database or search engine, enabling the chatbot to ground responses in authoritative sources and reduce hallucinations.","intents":["I want the chatbot to answer questions based on my product documentation or FAQs","I need the bot to cite sources when answering questions","I want to keep the knowledge base updated without retraining the chatbot"],"best_for":["businesses with large knowledge bases (product docs, FAQs, help articles) wanting to leverage them for chatbot training","customer support teams needing the chatbot to reference authoritative sources","companies in regulated industries (healthcare, finance, legal) requiring source attribution and traceability"],"limitations":["Document indexing and embedding generation can be slow for large knowledge bases (1000+ documents); initial setup may take hours","Semantic search quality depends on document structure and content quality; poorly formatted or ambiguous documents may not be retrieved correctly","Vector database queries add latency (100-500ms per query); response generation time scales with knowledge base size","No built-in document versioning or change tracking; updates to knowledge base may not be reflected immediately in chatbot responses"],"requires":["Knowledge base documents in supported formats (PDF, TXT, Markdown, HTML, or web URLs)","Document upload interface or API for ingestion","Optional: vector database or search engine for indexing (likely managed by platform)"],"input_types":["PDF, TXT, Markdown, or HTML documents","Web URLs for crawling and indexing","Structured data (FAQ pairs, Q&A datasets)"],"output_types":["indexed documents with embeddings","retrieved document snippets or full documents","chatbot responses with source citations"],"categories":["memory-knowledge","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":41,"verified":false,"data_access_risk":"high","permissions":["Web browser with modern JavaScript support (Chrome, Firefox, Safari, Edge)","Account creation on MyChatbots.AI platform","No programming knowledge required","Structured training data in supported formats (CSV, JSON, or plain text)","Minimum dataset size (likely 10-50 examples per intent, platform-dependent)","API key or authentication token for training job submission","Intent definitions and response templates for each supported language","Training data in each language (or translation of existing training data)","Optional: language detection model or explicit language selection UI","Conversation logs with user messages and bot responses"],"failure_modes":["Visual builders typically lack expressiveness for complex business logic — advanced conditional flows or dynamic data transformations may require workarounds or custom code","No-code abstractions often hide performance tuning options, making it difficult to optimize response latency for high-traffic scenarios","Drag-and-drop interfaces scale poorly for very large conversation trees (100+ intents), becoming unwieldy to navigate and maintain","Training on small datasets (< 100 examples) may lead to overfitting or poor generalization to out-of-domain queries","No visibility into which training examples influenced specific predictions, making debugging incorrect responses difficult","Training latency and cost scale with dataset size; very large datasets (10K+ examples) may incur significant processing time or fees","Platform likely does not support custom model architectures or hyperparameter tuning, limiting optimization for specific use cases","Multilingual models often have lower accuracy per language compared to monolingual models; language-specific nuances may be lost","Language detection can fail on code-mixed text (e.g., 'Hola, what's the status of my order?'); the bot may misclassify the intended language","Translation of knowledge base documents may introduce errors or loss of meaning; human review is recommended for critical content","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.31666666666666665,"quality":0.72,"ecosystem":0.25,"match_graph":0.25,"freshness":0.75,"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":"2026-05-24T12:16:31.858Z","last_scraped_at":"2026-04-05T13:23:42.560Z","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=mychatbots-ai","compare_url":"https://unfragile.ai/compare?artifact=mychatbots-ai"}},"signature":"Tlsf/u7Fyv56JTNrzRPkdZdIMkOPbCEucO8pmSGtG6kV5DmI9sxf2yiIvPYGjShfu2ACJzjsPlNkheo5F2TWCQ==","signedAt":"2026-06-20T08:21:12.774Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/mychatbots-ai","artifact":"https://unfragile.ai/mychatbots-ai","verify":"https://unfragile.ai/api/v1/verify?slug=mychatbots-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"}}