sms-based natural language query processing
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.
Unique: Routes SMS queries directly to LLM inference without requiring app installation or login, using carrier infrastructure as the transport layer rather than proprietary push notifications or web sockets. Handles SMS encoding constraints and multi-message reconstruction transparently.
vs alternatives: Eliminates app friction entirely compared to ChatGPT, Claude, or Copilot, making it accessible to users who won't download another app but already have SMS open.
stateless multi-turn conversation with implicit context recovery
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.
Unique: Reconstructs conversation context from SMS message history without requiring explicit session tokens or user-managed state — the phone number itself becomes the session identifier, and prior messages are automatically injected into the LLM prompt as conversation history.
vs alternatives: Provides multi-turn conversation continuity over SMS (which has no native session concept) without the friction of web-based chat interfaces, though with shallower context windows than dedicated chatbot platforms.
task automation and scheduling via natural language commands
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.
Unique: Converts SMS commands into structured task automation without requiring users to learn syntax or open separate apps — intent classification happens server-side and routes to appropriate backend services (calendar, reminders, timers, smart home APIs).
vs alternatives: More accessible than IFTTT or Zapier for non-technical users because it accepts natural language SMS rather than visual workflows, but less flexible because automation scope is pre-built rather than user-configurable.
information retrieval and web search integration
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.
Unique: Integrates web search and real-time data APIs into SMS responses by classifying queries and routing to appropriate data sources, then applying aggressive summarization to fit SMS constraints while preserving the most relevant information.
vs alternatives: Provides real-time information lookup over SMS without requiring app switching, but with lower fidelity than dedicated search or weather apps due to character limits and summarization requirements.
freemium usage metering and rate limiting
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.
Unique: Implements freemium metering at the SMS level using phone number-based user identification and daily/monthly quota tracking, with notifications delivered via SMS itself rather than in-app dashboards.
vs alternatives: Simple and transparent for SMS-first users, but less sophisticated than web-based SaaS metering because it lacks detailed usage dashboards and per-minute rate limiting.
intent classification and command routing
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.
Unique: Classifies SMS query intent server-side to route to specialized handlers (search, calendar, LLM, etc.) without requiring users to specify which service to use — the system infers intent from natural language and applies appropriate processing pipeline.
vs alternatives: Provides seamless multi-capability experience over SMS by hiding routing complexity, but less accurate than explicit user-specified routing (e.g., 'search: nearest coffee shop') because classification is probabilistic.
sms response formatting and character limit optimization
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.
Unique: Applies post-processing to LLM responses to fit SMS character constraints through intelligent abbreviation, emoji substitution, and multi-message splitting, rather than truncating or refusing to answer long queries.
vs alternatives: Enables substantive responses over SMS despite character limits, but with lower fidelity than web-based chat because formatting and detail must be sacrificed for brevity.
carrier-agnostic sms transport and delivery
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.
Unique: Uses a carrier-agnostic SMS gateway to abstract away carrier-specific delivery quirks and integrations, enabling single-API SMS support across all major carriers without direct carrier relationships.
vs alternatives: Simplifies SMS delivery compared to managing carrier APIs directly, but adds latency and cost compared to proprietary carrier integrations or push notifications.
+2 more capabilities