{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_tekst","slug":"tekst","name":"Tekst","type":"product","url":"https://www.tekst.com","page_url":"https://unfragile.ai/tekst","categories":["automation"],"tags":[],"pricing":{"model":"paid","free":false,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_tekst__cap_0","uri":"capability://tool.use.integration.multi.channel.message.ingestion.and.normalization","name":"multi-channel message ingestion and normalization","description":"Tekst ingests customer messages from multiple communication channels (email, SMS, chat, social media) and normalizes them into a unified message format before routing to workflows. The platform uses channel-specific adapters that translate protocol-specific metadata (sender IDs, timestamps, attachments) into a common schema, enabling downstream workflow logic to operate channel-agnostically without reimplementation per channel.","intents":["I need to handle customer inquiries from email, SMS, and chat in a single system without building separate integrations","I want to ensure message metadata is consistent regardless of which channel a customer uses","I need to preserve channel context (e.g., SMS character limits, email threading) while processing messages uniformly"],"best_for":["mid-market B2B companies with omnichannel customer bases","support teams managing 5+ communication channels","organizations needing unified audit trails across channels"],"limitations":["Channel adapter coverage is limited to major platforms; custom channels require custom adapter development","Message normalization may lose channel-specific formatting (e.g., rich text from Slack becomes plain text)","Attachment handling varies by channel; some channels have size/type restrictions that aren't abstracted away"],"requires":["API credentials for each enabled communication channel","Network connectivity to channel provider APIs","Message queue or event streaming infrastructure for high-volume ingestion (optional but recommended)"],"input_types":["email (SMTP, IMAP, API)","SMS (Twilio, AWS SNS, native gateways)","chat platforms (Slack, Teams, custom webhooks)","social media (Facebook Messenger, Twitter DMs)"],"output_types":["normalized message objects (JSON)","structured metadata (sender, timestamp, channel, thread ID)","attachment references with channel-native URLs"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_tekst__cap_1","uri":"capability://safety.moderation.end.to.end.encrypted.message.storage.and.transmission","name":"end-to-end encrypted message storage and transmission","description":"Tekst encrypts all customer messages at rest and in transit using TLS 1.3 for network transport and AES-256-GCM for storage encryption. The platform implements key management with per-tenant encryption keys, ensuring that even Tekst infrastructure cannot decrypt customer data without explicit key access. Encryption is applied at the message ingestion point before any processing, and decryption occurs only at the point of display or workflow execution.","intents":["I need to ensure customer messages are encrypted end-to-end to comply with GDPR, HIPAA, or PCI-DSS regulations","I want encryption keys to remain under my control, not managed by the SaaS provider","I need audit logs showing which users accessed encrypted data and when"],"best_for":["regulated industries (healthcare, finance, legal) handling sensitive customer data","companies with strict data residency or sovereignty requirements","enterprises requiring customer-managed encryption keys (BYOK)"],"limitations":["End-to-end encryption prevents Tekst from performing server-side AI analysis (sentiment analysis, intent classification) on message content without decryption","Key rotation requires careful coordination to avoid message decryption failures during transition periods","Encrypted search is not supported; full-text search requires decryption, adding latency"],"requires":["TLS 1.3 support on client and server","Key management infrastructure (AWS KMS, Azure Key Vault, or self-hosted HSM)","Compliance framework documentation (GDPR, HIPAA, PCI-DSS) for audit purposes"],"input_types":["plaintext messages from channels","encryption keys (RSA-2048 or higher, or symmetric keys)"],"output_types":["encrypted message blobs (AES-256-GCM ciphertext)","encryption metadata (key ID, algorithm, timestamp)","audit logs (access events, key rotation events)"],"categories":["safety-moderation","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_tekst__cap_10","uri":"capability://text.generation.language.response.template.library.and.quick.replies","name":"response template library and quick replies","description":"Tekst provides a library of pre-written response templates that agents can use to quickly reply to common customer inquiries. Templates support variable substitution (e.g., {{customer_name}}, {{ticket_id}}) and conditional sections (e.g., show billing info only if category is 'billing'). Agents can search templates by keyword, create custom templates, and track template usage. Templates can be organized by category and shared across teams. The system suggests relevant templates based on message category or customer history.","intents":["I want agents to respond to common questions (e.g., 'How do I reset my password?') with pre-written templates to save time","I need to ensure consistent messaging across the support team by using approved templates","I want to track which templates are most effective (highest customer satisfaction, fastest resolution)"],"best_for":["support teams handling repetitive inquiries","organizations with brand voice guidelines requiring consistent messaging","teams wanting to reduce response time and improve consistency"],"limitations":["Templates are static; no dynamic content generation based on customer data (requires manual variable substitution)","Template suggestions are rule-based (category matching); no ML-based relevance ranking","Templates don't account for conversation context; agents must manually edit for relevance","No A/B testing of templates; no data on which templates drive better outcomes"],"requires":["Template library (database or file storage)","Template variables (customer_name, ticket_id, etc.)","Template categories and tags"],"input_types":["template text (with variables and conditionals)","message category (for template suggestions)","customer data (for variable substitution)"],"output_types":["rendered response text (with variables substituted)","template suggestions (list of relevant templates)","template usage metrics (frequency, customer satisfaction)"],"categories":["text-generation-language","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_tekst__cap_11","uri":"capability://memory.knowledge.customer.conversation.history.and.context.retrieval","name":"customer conversation history and context retrieval","description":"Tekst maintains a complete conversation history for each customer across all channels and time periods, enabling agents to view full context when responding to new messages. The system automatically retrieves relevant past conversations (e.g., previous issues, purchases, complaints) and displays them alongside the current message. Context includes message text, attachments, resolution status, and associated tickets. Agents can manually search for specific past conversations or use AI-powered context suggestions (if enabled).","intents":["When a customer messages again, I want to see their full history so I don't ask them to repeat information","I need to understand if this is a repeat issue or a new problem by reviewing past conversations","I want to see what was promised in previous interactions to ensure consistency"],"best_for":["support teams handling repeat customers with long interaction histories","organizations prioritizing customer experience and context awareness","teams using Tekst's multi-channel integration to correlate conversations across channels"],"limitations":["Context retrieval is manual (agent-initiated search) or rule-based (last N conversations); no ML-based relevance ranking","Large conversation histories (100+ messages) may be slow to load and display","Cross-channel context correlation is limited; conversations on different channels are not automatically linked","Encrypted messages require decryption to display context, adding latency"],"requires":["Customer identity (email, account ID, phone number)","Conversation history storage (database)","Optional: decryption keys for encrypted messages"],"input_types":["customer ID","search query (optional, for manual context retrieval)","conversation filters (date range, channel, category)"],"output_types":["conversation history (list of past messages with metadata)","context summary (key issues, resolutions, promises)","related tickets or issues"],"categories":["memory-knowledge","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_tekst__cap_12","uri":"capability://data.processing.analysis.performance.analytics.and.reporting.dashboard","name":"performance analytics and reporting dashboard","description":"Tekst provides dashboards and reports showing key support metrics: message volume, response time, resolution time, customer satisfaction (CSAT), agent utilization, and SLA compliance. Metrics are aggregated by time period (daily, weekly, monthly), team, agent, and category. Reports can be scheduled and emailed automatically. The system supports custom metrics and KPIs via formula-based calculations. Data is visualized in charts (line, bar, pie) and tables for easy analysis.","intents":["I want to see how many messages we're handling per day and how fast we're responding","I need to identify underperforming agents or teams to provide coaching","I want to track SLA compliance to ensure we're meeting customer commitments"],"best_for":["support managers and directors tracking team performance","organizations with SLA commitments requiring compliance monitoring","teams using data-driven approaches to improve support efficiency"],"limitations":["Metrics are calculated from historical data; no real-time dashboards (typically 5-30 minute lag)","Custom metrics require formula definition; no drag-and-drop metric builder","CSAT data requires customer surveys; Tekst doesn't include survey collection","Benchmarking against industry standards is not provided; requires manual comparison"],"requires":["Message and ticket data (volume, timestamps, resolution status)","Agent and team definitions","Optional: CSAT survey data (from external survey tool)"],"input_types":["message events (arrival, response, resolution)","agent assignments and status changes","SLA definitions (response time, resolution time)","CSAT scores (if available)"],"output_types":["dashboard visualizations (charts, tables)","scheduled reports (PDF, email)","metric data (JSON, CSV export)","trend analysis (YoY, MoM comparisons)"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_tekst__cap_2","uri":"capability://planning.reasoning.intelligent.message.categorization.and.routing","name":"intelligent message categorization and routing","description":"Tekst uses rule-based and machine-learning-based categorization to automatically classify incoming messages by intent, urgency, or topic, then routes them to appropriate teams or workflows. The system learns from historical message labels and routing decisions, building a classifier that improves over time. Routing rules are expressed as a declarative workflow language that supports conditional logic (if-then-else), team assignment, priority escalation, and SLA-based queuing.","intents":["I want to automatically route billing inquiries to the finance team and technical issues to engineering without manual triage","I need urgent messages (e.g., account lockouts) to skip the queue and go directly to senior support staff","I want to learn from past routing decisions to improve categorization accuracy over time"],"best_for":["support teams handling 100+ messages per day across multiple topics","organizations with specialized teams requiring intelligent message distribution","companies wanting to reduce manual triage overhead"],"limitations":["ML-based categorization requires labeled training data (typically 500+ examples per category) to achieve >85% accuracy","Rule-based routing can become brittle if business logic changes frequently; requires workflow updates","Categorization accuracy degrades on out-of-distribution messages (e.g., new product launches, crisis events)","No real-time model retraining; updates require manual redeployment"],"requires":["Historical message data with labels (for ML training)","Workflow definition in Tekst's DSL or JSON format","Team/queue definitions in the system","Optional: custom ML model endpoint for advanced classification"],"input_types":["normalized message objects (from multi-channel ingestion)","message metadata (sender, channel, timestamp)","workflow rules (JSON or DSL)"],"output_types":["category label (string)","confidence score (0-1)","routing decision (team ID, queue, priority level)","SLA assignment (response time, resolution time)"],"categories":["planning-reasoning","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_tekst__cap_3","uri":"capability://automation.workflow.workflow.automation.with.conditional.logic.and.state.management","name":"workflow automation with conditional logic and state management","description":"Tekst provides a workflow engine that executes multi-step automation sequences triggered by message events (arrival, categorization, customer response). Workflows are defined declaratively using a state machine pattern, supporting branching (if-then-else), loops, delays, and external action invocations (API calls, CRM updates, email sends). The engine maintains workflow state across message interactions, enabling context-aware responses and multi-turn automation.","intents":["I want to automatically send a confirmation email when a customer submits a support ticket, then escalate to a human if they don't respond within 24 hours","I need to update our CRM when a customer message arrives, then trigger a follow-up workflow based on the CRM response","I want to create a chatbot-like flow that asks clarifying questions and routes based on customer answers"],"best_for":["support teams automating repetitive multi-step processes","organizations integrating Tekst with CRM, ticketing, or billing systems","teams building semi-automated support flows with human handoff points"],"limitations":["Workflow definitions can become complex and hard to debug for deeply nested conditional logic (>5 levels)","State management is in-memory by default; requires external persistence for high-availability deployments","No built-in workflow versioning; updating a workflow affects all in-flight instances","Limited error handling; failed external API calls require manual retry configuration"],"requires":["Workflow definition in Tekst's DSL or JSON format","Integration credentials for external systems (CRM, email, APIs)","Event schema definition (what triggers workflows)","Optional: external state store (Redis, DynamoDB) for persistence"],"input_types":["message events (arrival, response, categorization)","workflow definitions (JSON/DSL)","external API responses (for conditional branching)","customer/ticket data (from CRM or database)"],"output_types":["workflow execution logs (step-by-step trace)","external API calls (HTTP requests to CRM, email, etc.)","state snapshots (for resumption after delays)","workflow completion status (success, failure, pending)"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_tekst__cap_4","uri":"capability://tool.use.integration.native.crm.and.helpdesk.system.integration","name":"native crm and helpdesk system integration","description":"Tekst provides pre-built connectors for popular CRM (Salesforce, HubSpot) and helpdesk (Jira Service Desk, Freshdesk) systems, enabling bidirectional data sync without custom API development. Integrations use webhook-based event streaming for real-time updates: when a message arrives in Tekst, customer data is fetched from the CRM; when a ticket is resolved in Tekst, the status is pushed back to the helpdesk. Integrations are configured through a UI with field mapping and transformation rules.","intents":["I want customer context from Salesforce to appear automatically in Tekst when a message arrives, without manual lookups","I need ticket status in Jira to update automatically when a support agent resolves an issue in Tekst","I want to avoid building custom API integrations and use pre-built connectors instead"],"best_for":["teams already using Salesforce, HubSpot, Jira, or Freshdesk","organizations wanting to minimize custom integration development","companies needing real-time bidirectional sync between systems"],"limitations":["Pre-built connectors cover only major CRM/helpdesk platforms; custom systems require custom API development","Field mapping is static; dynamic transformations require custom code or middleware","Sync latency is typically 5-30 seconds due to webhook processing; real-time sync is not guaranteed","Connector updates may break existing integrations if API contracts change"],"requires":["Active account with supported CRM or helpdesk system","API credentials (OAuth token, API key) for the external system","Network connectivity to external system APIs","Field mapping configuration (which Tekst fields map to which CRM fields)"],"input_types":["message events (from Tekst)","CRM/helpdesk API responses (customer data, ticket status)","field mapping rules (JSON)"],"output_types":["customer context (name, email, account status, history)","ticket updates (status, assignee, priority)","sync logs (success/failure events)"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_tekst__cap_5","uri":"capability://search.retrieval.message.search.and.retrieval.with.context.preservation","name":"message search and retrieval with context preservation","description":"Tekst indexes all messages and metadata (sender, timestamp, channel, category) in a searchable store, enabling full-text search across customer conversations. Search results return message snippets with surrounding context (previous/next messages in the thread) to help support agents understand conversation flow. Search supports filters (by date, channel, customer, category) and sorting (by relevance, recency, priority). For encrypted messages, search requires decryption, adding latency.","intents":["I want to find all messages from a specific customer across all channels to understand their history","I need to search for messages containing 'billing error' to identify common issues","I want to retrieve a conversation thread with full context to hand off to another agent"],"best_for":["support teams needing to investigate customer issues across message history","organizations with large message volumes (100k+ messages) requiring fast search","teams using Tekst's encryption and needing to search encrypted data"],"limitations":["Full-text search on encrypted messages requires decryption, adding 100-500ms latency per search","Search index may lag behind real-time message ingestion by 5-30 seconds","Context preservation is limited to same-channel threads; cross-channel context requires manual correlation","Search does not support semantic/similarity search; only exact keyword and filter-based matching"],"requires":["Search index infrastructure (Elasticsearch, Solr, or proprietary)","Message data with metadata (timestamp, sender, channel, category)","Optional: decryption keys for searching encrypted messages"],"input_types":["search query (text string)","filters (date range, channel, customer ID, category)","sort criteria (relevance, recency, priority)"],"output_types":["message snippets (text excerpt)","message metadata (sender, timestamp, channel)","surrounding context (previous/next messages)","relevance score (for keyword search)"],"categories":["search-retrieval","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_tekst__cap_6","uri":"capability://automation.workflow.team.collaboration.and.message.assignment","name":"team collaboration and message assignment","description":"Tekst enables support teams to assign messages to individual agents or team queues, with visibility into assignment status, SLA timers, and agent workload. Agents can claim messages from shared queues, reassign to colleagues, or escalate to supervisors. The system tracks assignment history and provides dashboards showing queue depth, average resolution time, and agent utilization. Assignments can be automated via workflow rules (e.g., route to 'billing' team if category is 'billing').","intents":["I want to assign a customer message to the right agent based on their expertise and current workload","I need to see which messages are unassigned and how long they've been waiting","I want to escalate a complex issue to a supervisor without losing context"],"best_for":["support teams with multiple agents and specialized roles","organizations needing visibility into queue depth and SLA compliance","teams using Tekst's workflow automation to auto-assign messages"],"limitations":["Manual assignment requires agent intervention; no intelligent load-balancing based on agent skill or availability","SLA timers are simple countdown clocks; no predictive SLA breach warnings","Escalation is manual; no automatic escalation based on message age or complexity","No integration with external workforce management systems (e.g., Verint, NICE)"],"requires":["Team and agent definitions in Tekst","Queue configuration (team queues, SLA rules)","Optional: workflow rules for auto-assignment"],"input_types":["message objects (with category, priority)","agent availability status","team definitions"],"output_types":["assignment status (assigned to agent/queue, timestamp)","SLA timer (response deadline, resolution deadline)","queue metrics (depth, average wait time)","agent utilization (messages assigned, active, resolved)"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_tekst__cap_7","uri":"capability://safety.moderation.audit.logging.and.compliance.reporting","name":"audit logging and compliance reporting","description":"Tekst maintains immutable audit logs of all system actions: message access, encryption key usage, workflow executions, user logins, and configuration changes. Logs include actor (user/system), action, timestamp, and result (success/failure). The system generates compliance reports (GDPR data access, HIPAA audit trails, PCI-DSS access logs) that can be exported for regulatory review. Logs are stored separately from operational data and cannot be modified retroactively.","intents":["I need to prove to auditors that customer data was accessed only by authorized users","I want to generate a GDPR data access report showing who viewed a specific customer's messages","I need to investigate a security incident by reviewing all actions taken by a user during a specific time period"],"best_for":["regulated industries (healthcare, finance, legal) requiring audit trails","organizations undergoing compliance audits (SOC 2, ISO 27001, HIPAA, GDPR)","enterprises with security incident response requirements"],"limitations":["Audit logs can grow very large (100k+ entries per day for high-volume systems), requiring careful retention policies","Log queries on large datasets may be slow; requires indexing for fast retrieval","Compliance reports are generated on-demand; no real-time compliance monitoring","Log retention is configurable but not infinite; old logs may be archived or deleted per policy"],"requires":["Audit log storage infrastructure (database, data lake)","Log retention policy (how long to keep logs)","Compliance framework requirements (GDPR, HIPAA, PCI-DSS)"],"input_types":["system events (message access, key usage, login, config change)","actor identity (user ID, service account)","action details (what was accessed, what was changed)"],"output_types":["audit log entries (JSON or structured format)","compliance reports (PDF, CSV)","log queries (filtered by date, actor, action, resource)"],"categories":["safety-moderation","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_tekst__cap_8","uri":"capability://safety.moderation.customer.data.export.and.deletion.gdpr.privacy.compliance","name":"customer data export and deletion (gdpr/privacy compliance)","description":"Tekst provides APIs and UI tools to export all customer data (messages, metadata, attachments) in a portable format (JSON, CSV) and to permanently delete customer records on request. Deletion is performed securely: encrypted messages are deleted along with their encryption keys, making recovery impossible. The system tracks deletion requests in audit logs for compliance verification. Export and deletion can be triggered manually or via API for programmatic integration with privacy workflows.","intents":["A customer requests their data under GDPR Article 20 (right to data portability); I need to export it in a standard format","A customer requests deletion under GDPR Article 17 (right to be forgotten); I need to permanently remove all their data","I need to automate privacy requests by integrating Tekst's export/deletion APIs with our privacy management system"],"best_for":["organizations operating in GDPR jurisdictions (EU, UK, etc.)","companies with privacy-conscious customers requesting data access/deletion","enterprises automating privacy request workflows"],"limitations":["Export may be large (100MB+) for customers with long message histories; requires efficient streaming","Deletion is permanent and irreversible; no recovery option after deletion","Deletion latency depends on data volume; large deletions may take hours","Backup/archival systems may retain deleted data; requires coordination with backup retention policies"],"requires":["Customer identity verification (email, account ID)","API credentials for programmatic access","Optional: integration with privacy management platform"],"input_types":["customer ID or email","export format preference (JSON, CSV)","deletion request confirmation"],"output_types":["exported data file (JSON, CSV, ZIP)","deletion confirmation (timestamp, audit log entry)","export/deletion status (in progress, completed, failed)"],"categories":["safety-moderation","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_tekst__cap_9","uri":"capability://automation.workflow.real.time.message.notifications.and.agent.alerts","name":"real-time message notifications and agent alerts","description":"Tekst sends real-time notifications to agents when new messages arrive, SLAs are about to breach, or messages are assigned to them. Notifications are delivered via multiple channels (in-app, email, SMS, Slack) based on agent preferences. The system supports notification rules (e.g., 'alert me only for high-priority messages') and quiet hours (e.g., 'no notifications after 6 PM'). Notifications include message preview and action buttons (claim, assign, escalate) for quick response.","intents":["I want agents to be notified immediately when a high-priority message arrives so they can respond quickly","I need to alert supervisors when an SLA is about to breach so they can escalate","I want agents to customize notification preferences (channels, rules, quiet hours) without admin intervention"],"best_for":["support teams needing real-time message visibility","organizations with SLA requirements (response time <1 hour)","teams using multiple communication channels (Slack, email, SMS)"],"limitations":["Notification delivery latency is typically 1-5 seconds; real-time delivery is not guaranteed","Notification spam can occur if rules are too broad; requires careful tuning","SMS notifications incur per-message costs; may not be cost-effective for high-volume teams","Notification preferences are per-agent; no team-wide notification policies"],"requires":["Agent contact information (email, phone, Slack ID)","Notification channel credentials (email server, SMS gateway, Slack workspace)","Notification rules configuration"],"input_types":["message events (arrival, SLA breach, assignment)","message metadata (priority, category, customer)","agent notification preferences"],"output_types":["notifications (email, SMS, Slack, in-app)","notification logs (delivery status, timestamp)","agent preference updates"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":43,"verified":false,"data_access_risk":"high","permissions":["API credentials for each enabled communication channel","Network connectivity to channel provider APIs","Message queue or event streaming infrastructure for high-volume ingestion (optional but recommended)","TLS 1.3 support on client and server","Key management infrastructure (AWS KMS, Azure Key Vault, or self-hosted HSM)","Compliance framework documentation (GDPR, HIPAA, PCI-DSS) for audit purposes","Template library (database or file storage)","Template variables (customer_name, ticket_id, etc.)","Template categories and tags","Customer identity (email, account ID, phone number)"],"failure_modes":["Channel adapter coverage is limited to major platforms; custom channels require custom adapter development","Message normalization may lose channel-specific formatting (e.g., rich text from Slack becomes plain text)","Attachment handling varies by channel; some channels have size/type restrictions that aren't abstracted away","End-to-end encryption prevents Tekst from performing server-side AI analysis (sentiment analysis, intent classification) on message content without decryption","Key rotation requires careful coordination to avoid message decryption failures during transition periods","Encrypted search is not supported; full-text search requires decryption, adding latency","Templates are static; no dynamic content generation based on customer data (requires manual variable substitution)","Template suggestions are rule-based (category matching); no ML-based relevance ranking","Templates don't account for conversation context; agents must manually edit for relevance","No A/B testing of templates; no data on which templates drive better outcomes","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.36666666666666664,"quality":0.78,"ecosystem":0.15000000000000002,"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":"2026-05-24T12:16:33.648Z","last_scraped_at":"2026-04-05T13:23:42.551Z","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=tekst","compare_url":"https://unfragile.ai/compare?artifact=tekst"}},"signature":"55DUGsZReOWzi8gVeHfKRlPl1O5gPeHKe5NaGDTmFPfjdthLlTQkrUQBaH4PUyw44QeDbkJJ0J8mtfYBAPwnDg==","signedAt":"2026-06-21T16:54:04.232Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/tekst","artifact":"https://unfragile.ai/tekst","verify":"https://unfragile.ai/api/v1/verify?slug=tekst","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"}}