Have AI Assistant Right Beside Your Keyboard
BlockGram brings real-time, context-aware artificial intelligence directly into Telegram chats, turning each conversation into an intelligent interface. The AI assistant is embedded in the chat environment, offering actionable suggestions, parsing commands, summarizing discussions, generating replies, and enabling crypto interactions, all without leaving the messaging interface.
Core Capabilities of the AI Assistant
Inline Prompting and Completion
Suggests auto-completions for commands like “send 0.5 MATIC to…”
Summarizes recent messages on demand
Detects intents for payments, bill splitting, or portfolio updates and prompts users proactively
Proactive Context Analysis
Continuously monitors conversation for relevant triggers
Detects mentions of debts, expenses, or transactions
Suggests initiating payments or splitting bills
Recognizes wallet addresses and offers secure sending options
Multimodal Interaction
Supports typed natural language in major languages
Voice command recognition via speech-to-text integration
Structured quick actions for recent transactions, NFTs, or assets
Technical Architecture
Inference Pipeline
Input Parsing: User messages are tokenized and semantically embedded using lightweight transformer models
Intent Recognition: Classifies messages into categories such as payment, request, summary, schedule, or crypto transfer
Response Composition: Crafts context-aware replies or prepares actions based on detected intent
Action Dispatch: Executes AI-suggested actions via smart contracts or integrated APIs
Use Cases Within Chat
Instantly generate wallets or send crypto based on natural commands
Summarize group chats or DAO discussions in real time
Automate recurring payments or shared expense calculations
Provide portfolio insights or NFT ownership confirmations directly in chat
Customization and Control
Privacy-Aware Context Windows: Only recent relevant messages are processed; data isn’t permanently stored
On-Demand Invocation: Users choose whether AI acts automatically, via keyword triggers, or through manual slash commands
Model Switching: Advanced users can select lightweight local models or high-power remote inference
Privacy and Safety
On-Device Inference: Reduces latency and keeps sensitive data local when hardware supports it
No Data Retention: AI inputs are ephemeral unless encrypted and stored by the user
AI Explanation Layer: Before executing any action, users see what the AI interpreted and what it plans to do, allowing full manual confirmation
Benefits
Integrates financial intelligence and conversational support directly into Telegram
Reduces cognitive load and manual steps for crypto tasks
Provides a personalized assistant for everyday chat and financial workflows
Bridges natural language commands with blockchain operations, making crypto accessible without technical knowledge
Last updated