{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_hey-internet","slug":"hey-internet","name":"Hey Internet","type":"product","url":"https://heyinternet.ai","page_url":"https://unfragile.ai/hey-internet","categories":["chatbots-assistants"],"tags":[],"pricing":{"model":"freemium","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_hey-internet__cap_0","uri":"capability://text.generation.language.sms.based.natural.language.query.processing","name":"sms-based natural language query processing","description":"Accepts free-form text queries via SMS and routes them through an LLM inference pipeline that interprets intent from unstructured, often abbreviated mobile messaging syntax. The system handles SMS character limits (160-1600 chars depending on encoding) by chunking long queries and reconstructing context server-side, then returns responses formatted to fit SMS constraints with intelligent truncation or multi-message splitting.","intents":["Ask quick factual questions without opening an app","Get instant answers while in meetings or on the go","Submit queries in natural conversational tone without formal prompting"],"best_for":["Mobile-first users who live in SMS/messaging apps","Professionals needing sub-30-second response latency","Users in regions where SMS is more reliable than data connectivity"],"limitations":["SMS character encoding limits queries to ~160-1600 characters depending on special characters, forcing brevity that may lose nuance","No rich formatting support (markdown, code blocks, tables) — responses must be plain text or emoji-enhanced","Latency varies by carrier and network conditions; no guaranteed response time SLA","No conversation threading or message grouping — each SMS is treated as independent unless explicitly referenced"],"requires":["Active phone number with SMS capability","Carrier support for inbound/outbound SMS (not available in all regions)","Freemium account registration (email or phone)"],"input_types":["plain text SMS","abbreviated/colloquial language","emoji and special characters"],"output_types":["plain text SMS response","multi-message SMS chains for longer responses","emoji-enhanced formatting"],"categories":["text-generation-language","mobile-first"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hey-internet__cap_1","uri":"capability://memory.knowledge.stateless.multi.turn.conversation.with.implicit.context.recovery","name":"stateless multi-turn conversation with implicit context recovery","description":"Maintains conversation state across multiple SMS exchanges by storing message history server-side and reconstructing context from previous queries in the same thread. Uses phone number + timestamp-based message grouping to associate related queries, then injects prior exchange summaries into the LLM prompt to simulate multi-turn awareness without requiring explicit session management from the user.","intents":["Ask follow-up questions that reference earlier answers","Refine or clarify a previous query without repeating context","Maintain a logical conversation flow across multiple SMS exchanges"],"best_for":["Users asking sequential questions on the same topic","Scenarios requiring clarification or iteration (e.g., 'make it shorter', 'explain that more')","Mobile users who expect chat-like continuity from SMS"],"limitations":["Context window is limited to recent message history (likely 5-10 prior exchanges) due to SMS latency and token budget constraints","No explicit conversation reset mechanism — users cannot easily start fresh without waiting for context to age out","Implicit context recovery may fail if messages are sent from different phone numbers or after long delays (>24 hours)","Cannot reference specific message IDs or timestamps — only sequential ordering"],"requires":["Consistent phone number across messages","Messages sent within a reasonable time window (likely <24 hours)","Server-side message history storage (implies privacy/data retention policy)"],"input_types":["sequential SMS messages","follow-up queries","refinement requests"],"output_types":["contextually-aware SMS responses","responses that reference prior exchanges"],"categories":["memory-knowledge","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hey-internet__cap_2","uri":"capability://automation.workflow.task.automation.and.scheduling.via.natural.language.commands","name":"task automation and scheduling via natural language commands","description":"Interprets natural language commands in SMS (e.g., 'remind me to call mom at 3pm', 'set a timer for 20 minutes', 'add milk to my shopping list') and translates them into executable actions via integration with device calendars, reminders, timers, and note-taking services. Uses intent classification to route commands to appropriate backend services (calendar API, reminder service, etc.) and returns confirmation via SMS.","intents":["Create reminders and calendar events without opening calendar app","Set timers and alarms via text message","Add items to shopping lists or to-do lists without context switching","Automate routine tasks (e.g., 'turn on my lights') via natural language"],"best_for":["Busy professionals who need quick task capture without app switching","Users with smart home devices who want voice-like control via SMS","Teams using SMS as a primary communication channel"],"limitations":["Automation scope is limited to integrations Hey Internet has built (likely calendar, reminders, timers, notes) — no custom webhook or IFTTT support","Natural language intent classification may fail on ambiguous commands (e.g., 'call mom' could mean phone call, video call, or send message)","No confirmation dialog for destructive actions — relies on user re-reading confirmation SMS","Scheduling precision is limited by SMS latency; sub-minute timing guarantees are not feasible","Smart home integration (if present) likely requires separate account linking and OAuth setup"],"requires":["Freemium account with permissions granted for calendar/reminder/timer access","Device or service integrations enabled (Google Calendar, Apple Reminders, etc.)","For smart home: separate account linking (e.g., Philips Hue, IFTTT)"],"input_types":["natural language SMS commands","time expressions (e.g., '3pm', 'in 20 minutes', 'tomorrow at 9am')","task descriptions"],"output_types":["confirmation SMS","calendar events","reminder notifications","timer/alarm triggers"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hey-internet__cap_3","uri":"capability://search.retrieval.information.retrieval.and.web.search.integration","name":"information retrieval and web search integration","description":"Processes SMS queries that require real-time information (e.g., 'what's the weather', 'stock price of AAPL', 'nearest coffee shop') by routing them to web search APIs or structured data services, then synthesizing results into SMS-friendly summaries. Uses query classification to determine whether a response requires live data or can be answered from LLM training data, and applies result ranking/filtering to fit SMS character constraints.","intents":["Get current weather, traffic, or news without opening a weather app","Look up stock prices, sports scores, or live event information","Find nearby restaurants, stores, or services via location-based search","Verify facts or get current information that may have changed since LLM training"],"best_for":["Users needing quick factual lookups while mobile","Scenarios where opening a browser or app is impractical","Professionals who need real-time data (stocks, weather, news) integrated into SMS workflow"],"limitations":["Search results must be heavily summarized to fit SMS character limits — nuance and detail are lost","No pagination or 'show more' mechanism — users get one best result or a ranked list of 2-3 options","Location-based search requires location permission or manual entry, adding friction","Search quality depends on underlying APIs (Google Search, weather services, etc.) — Hey Internet has no control over result accuracy","Real-time data freshness varies by source (stock prices may be delayed by 15+ minutes)"],"requires":["Active internet connection","Location permission (for location-based queries)","API keys for search/data services (Google Search, weather API, etc.)"],"input_types":["natural language queries requiring real-time data","location-based queries","factual lookup requests"],"output_types":["summarized search results in SMS format","structured data (weather, stock prices, scores)","ranked lists of options"],"categories":["search-retrieval","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hey-internet__cap_4","uri":"capability://automation.workflow.freemium.usage.metering.and.rate.limiting","name":"freemium usage metering and rate limiting","description":"Implements a freemium model where free-tier users receive a limited number of queries per day/month (likely 10-50 per day) before hitting rate limits, while paid users get unlimited or higher quotas. Uses phone number-based user identification to track usage, applies token-bucket or sliding-window rate limiting, and returns SMS notifications when limits are approached or exceeded.","intents":["Understand how many queries I have left in my free tier","Upgrade to paid plan when I hit rate limits","Track my usage patterns to decide if paid tier is worth it"],"best_for":["Freemium SaaS products that need to balance free user acquisition with monetization","Products targeting price-sensitive mobile users who expect free trials","Teams evaluating whether to upgrade based on actual usage"],"limitations":["Rate limiting is coarse-grained (daily or monthly) — no per-minute or per-hour limits, so users could theoretically burst all queries at once","No usage dashboard or detailed breakdown — users only see 'X queries remaining' via SMS","Upgrade path requires leaving SMS to visit website or app, creating friction at the moment of conversion","No grace period or overage handling — users hit a hard limit and cannot query further without upgrading","Phone number-based identification means shared phones or family accounts may hit limits unexpectedly"],"requires":["Freemium account registration","Phone number as unique identifier","Payment method on file for paid tier (if upgrading)"],"input_types":["SMS queries (counted against quota)"],"output_types":["SMS responses (when within quota)","rate limit notification SMS","upgrade prompts"],"categories":["automation-workflow","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hey-internet__cap_5","uri":"capability://planning.reasoning.intent.classification.and.command.routing","name":"intent classification and command routing","description":"Analyzes incoming SMS queries to classify intent (e.g., 'factual question', 'task creation', 'web search', 'calculation', 'creative writing') and routes them to appropriate backend handlers. Uses a lightweight classification model (likely fine-tuned LLM or rule-based heuristics) that runs server-side to determine which service should handle the query, enabling specialized handling for different query types without exposing complexity to the user.","intents":["Route factual questions to web search when needed","Detect task creation commands and trigger calendar/reminder integrations","Identify creative or open-ended queries that need full LLM reasoning","Classify queries that require calculation or data processing"],"best_for":["Multi-capability systems that need to route queries intelligently","Products that integrate multiple backend services (search, calendar, LLM, etc.)","Teams building SMS-based assistants that need to optimize response latency per query type"],"limitations":["Intent classification is imperfect — ambiguous queries may be routed to wrong handler (e.g., 'call mom' routed to calendar instead of phone)","No user feedback loop to correct misclassifications — users cannot easily tell the system 'that was wrong'","Classification latency adds 100-500ms to response time before actual query processing begins","Limited to pre-defined intent categories — novel or hybrid intents may not be recognized","No confidence scoring exposed to user — system commits to a routing decision without hedging"],"requires":["Intent classification model (trained or rule-based)","Backend handlers for each intent type (search API, calendar API, LLM, etc.)","Server-side processing pipeline"],"input_types":["natural language SMS queries"],"output_types":["routed to appropriate backend handler","specialized response format per intent type"],"categories":["planning-reasoning","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hey-internet__cap_6","uri":"capability://text.generation.language.sms.response.formatting.and.character.limit.optimization","name":"sms response formatting and character limit optimization","description":"Automatically formats LLM responses to fit SMS character constraints (160 characters for single SMS, or splits into multiple messages) while preserving readability and information density. Uses techniques like abbreviation expansion, emoji substitution, and intelligent truncation to maximize content within limits, and implements multi-message chaining with implicit continuation markers (e.g., '(1/3)') to signal multi-part responses.","intents":["Receive complete answers to complex questions despite SMS character limits","Read responses that are formatted for mobile readability","Understand when a response spans multiple SMS messages"],"best_for":["SMS-based AI assistants that need to return substantive responses","Mobile-first products where users expect readable formatting","Systems integrating with carriers that enforce strict SMS length limits"],"limitations":["Character limit forces aggressive summarization — nuance and detail are lost compared to web-based responses","Multi-message responses may arrive out of order or with delays between messages, confusing users","No rich formatting (bold, italics, code blocks, tables) — responses are plain text with emoji enhancements only","Abbreviations and truncation reduce clarity for users unfamiliar with shorthand","No way to request 'full response' — users cannot opt into longer, more detailed answers"],"requires":["SMS carrier support for multi-part messages (concatenated SMS)","Character encoding awareness (UTF-8 vs GSM 7-bit affects character count)"],"input_types":["LLM-generated responses (any length)"],"output_types":["SMS-formatted responses","single or multi-part SMS messages","emoji-enhanced plain text"],"categories":["text-generation-language","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hey-internet__cap_7","uri":"capability://tool.use.integration.carrier.agnostic.sms.transport.and.delivery","name":"carrier-agnostic sms transport and delivery","description":"Abstracts away carrier-specific SMS delivery by using a carrier-agnostic SMS gateway (likely Twilio, AWS SNS, or similar) to send and receive messages across all major carriers (Verizon, AT&T, T-Mobile, etc.). Handles carrier-specific quirks (e.g., message splitting, encoding differences, delivery delays) transparently, and provides basic delivery status tracking (sent, delivered, failed) via server-side logging.","intents":["Send and receive SMS from any carrier without integration complexity","Ensure messages are delivered reliably across different networks","Handle carrier-specific SMS limitations (length, encoding, etc.) automatically"],"best_for":["SMS-based products that need to work across all carriers","Teams that don't want to manage carrier integrations directly","Products requiring reliable SMS delivery without building carrier relationships"],"limitations":["Carrier-agnostic gateways add latency (typically 1-5 seconds per message) compared to direct carrier APIs","Delivery is not guaranteed — SMS can fail silently or be delayed by hours in rare cases","No delivery receipts for all carriers — some carriers don't support delivery confirmation","Cost per SMS (typically $0.01-0.05) adds up at scale, making SMS less cost-effective than push notifications","Carrier filtering and spam detection may block Hey Internet's messages if reputation is poor"],"requires":["SMS gateway account (Twilio, AWS SNS, etc.)","API credentials and rate limits configured","Phone number provisioned with gateway"],"input_types":["outbound SMS messages","inbound SMS from users"],"output_types":["SMS delivery status","inbound message routing to application"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hey-internet__cap_8","uri":"capability://safety.moderation.phone.number.based.user.identification.and.privacy","name":"phone number-based user identification and privacy","description":"Uses phone number as the primary user identifier (no email, username, or password required) to enable zero-friction signup and authentication. Stores minimal user data (phone number, usage quota, preferences) server-side and relies on SMS itself as the authentication mechanism — incoming SMS from a registered phone number is implicitly authenticated. Implements basic privacy controls (e.g., ability to delete account and associated message history).","intents":["Sign up for Hey Internet without creating an account or password","Authenticate subsequent SMS queries using phone number alone","Delete my account and message history if I want to stop using the service"],"best_for":["Mobile-first products targeting users who avoid account creation friction","Services where phone number is a natural identifier (SMS-based)","Privacy-conscious users who prefer minimal data collection"],"limitations":["Phone number is not a unique identifier — shared phones, family plans, or number recycling can cause account conflicts","No password recovery mechanism — if phone is lost or number is reassigned, account access is lost","Minimal user data means no personalization or preference learning across sessions","Privacy is limited to account deletion — message history may be retained server-side for compliance/debugging","No way to link multiple phone numbers to a single account (e.g., work + personal phones)","SMS itself is not encrypted — messages are transmitted in plain text over carrier networks"],"requires":["Active phone number with SMS capability","Acceptance of privacy policy and data retention terms"],"input_types":["phone number (for signup)","SMS messages (for authentication)"],"output_types":["account confirmation SMS","authentication via SMS"],"categories":["safety-moderation","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hey-internet__cap_9","uri":"capability://text.generation.language.latency.optimized.response.generation.for.mobile","name":"latency-optimized response generation for mobile","description":"Optimizes LLM inference latency for SMS use cases by using smaller, faster models (likely distilled or quantized versions of larger models) that prioritize response speed over maximum quality. Implements response streaming and early truncation — if a response is taking too long to generate, the system returns a partial response rather than timing out. Uses server-side caching of common queries to avoid redundant inference.","intents":["Get responses in under 5 seconds (typical SMS expectation)","Avoid timeouts or 'no response' failures when inference is slow","Reuse cached responses for frequently asked questions"],"best_for":["Mobile users who expect sub-5-second response times","High-volume SMS services where latency directly impacts user experience","Products where response speed is more important than maximum quality"],"limitations":["Smaller/faster models produce lower-quality responses compared to full-size LLMs (e.g., GPT-4)","Response streaming and truncation may result in incomplete or cut-off answers","Caching only helps for exact query matches — paraphrased versions of common questions won't hit cache","Latency optimization trades off reasoning depth — complex multi-step problems may not be solved well","No way for users to request 'higher quality, slower response' — system always optimizes for speed"],"requires":["Smaller/faster LLM model (likely distilled or quantized)","Response caching infrastructure (Redis, memcached, etc.)","Streaming inference capability"],"input_types":["SMS queries"],"output_types":["fast SMS responses (sub-5 seconds)","potentially truncated responses"],"categories":["text-generation-language","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":40,"verified":false,"data_access_risk":"high","permissions":["Active phone number with SMS capability","Carrier support for inbound/outbound SMS (not available in all regions)","Freemium account registration (email or phone)","Consistent phone number across messages","Messages sent within a reasonable time window (likely <24 hours)","Server-side message history storage (implies privacy/data retention policy)","Freemium account with permissions granted for calendar/reminder/timer access","Device or service integrations enabled (Google Calendar, Apple Reminders, etc.)","For smart home: separate account linking (e.g., Philips Hue, IFTTT)","Active internet connection"],"failure_modes":["SMS character encoding limits queries to ~160-1600 characters depending on special characters, forcing brevity that may lose nuance","No rich formatting support (markdown, code blocks, tables) — responses must be plain text or emoji-enhanced","Latency varies by carrier and network conditions; no guaranteed response time SLA","No conversation threading or message grouping — each SMS is treated as independent unless explicitly referenced","Context window is limited to recent message history (likely 5-10 prior exchanges) due to SMS latency and token budget constraints","No explicit conversation reset mechanism — users cannot easily start fresh without waiting for context to age out","Implicit context recovery may fail if messages are sent from different phone numbers or after long delays (>24 hours)","Cannot reference specific message IDs or timestamps — only sequential ordering","Automation scope is limited to integrations Hey Internet has built (likely calendar, reminders, timers, notes) — no custom webhook or IFTTT support","Natural language intent classification may fail on ambiguous commands (e.g., 'call mom' could mean phone call, video call, or send message)","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.31666666666666665,"quality":0.72,"ecosystem":0.2,"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":"2026-05-24T12:16:30.893Z","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=hey-internet","compare_url":"https://unfragile.ai/compare?artifact=hey-internet"}},"signature":"NEMJID+/F9y4oWCJmWJx4WAqWQZe+BMQs5kjQHzKJyUReyUILCN0bLWmQdjjaBJ/33NKslXqHCIsLwExTnNuDQ==","signedAt":"2026-06-20T09:55:59.549Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/hey-internet","artifact":"https://unfragile.ai/hey-internet","verify":"https://unfragile.ai/api/v1/verify?slug=hey-internet","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"}}