Fluent

Problem Statement

Fluent is an AI-powered Web3 learning platform that transforms how people understand blockchain concepts. Instead of reading static documentation or watching endless YouTube tutorials, users learn by highlighting any Web3 sentence or concept directly in their browser and receiving instant, personalized explanations.

Solution

Architecture Overview Fluent combines a browser extension frontend, an AI-powered agent backend, and blockchain infrastructure to create a seamless learning experience.Core Technologies & IntegrationBrowser Extension (JavaScript/Chrome Extension API)Content scripts inject into any webpage to detect text selectionCaptures highlighted sentences and sends them to the backend agentDisplays real-time explanations in a floating tooltip UIBuilt with vanilla JavaScript for maximum compatibilityAI Agent Backend (Python + uAgents Framework)uAgents: Fetch.ai's autonomous agent framework handles all backend logicASI:One Integration: Uses three specialized models:asi1-mini: Core concept extraction and explanation generationasi1-graph: Advanced graph reasoning and learning path optimizationasi1-agentic: Multi-step reasoning for complex queriesMeTTa Knowledge Graph: Symbolic reasoning engine that stores user's learning as queryable graph nodes and relationshipsRuns as a mailbox agent, discoverable on Agentverse while hosting local REST endpointsReal-Time Blockchain Data (Blockscout MCP)Integrates Blockscout's Model Context Protocol for live on-chain examplesWhen explaining "relayers," shows actual recent relayer transactions on BaseEnriches static definitions with real transaction data, gas costs, and contract interactionsUses REST API calls to https://mcp.blockscout.com/mcp for chain-agnostic dataDatabase & User Management (Supabase)PostgreSQL database with real-time subscriptionsStores captured sentences, user knowledge graphs, quiz results, and NFT metadataRow-level security for multi-user supportGoogle OAuth integration for seamless authenticationSoulbound NFT System (Solidity + Base)Custom ERC-721 contract deployed on Base SepoliaQuiz-gated minting: users must score 80%+ to earn domain badgesNon-transferable tokens serve as verifiable learning credentialsMetadata stored on IPFS via Pinata, includes user's knowledge subgraphFrontend Dashboard (Next.js + React)Visualizes user's knowledge graph with interactive node-link diagramsDomain-specific views (DeFi, L2s, DAOs) with progress trackingBadge gallery showing earned NFT credentialsReal-time updates via Supabase subscriptionsPartner Technology Benefits ASI Alliance Stack (uAgents + ASI:One + MeTTa)uAgents provided the perfect framework for building stateful, conversational AI that can handle both REST endpoints and agent-to-agent communicationASI:One models were specifically designed for agentic workflows, making concept extraction and graph reasoning much more reliable than generic LLMsMeTTa enabled true explainable AI—users can see exactly what the system knows and why, crucial for educational applicationsBlockscout MCPTransformed static explanations into live, contextual learning with real transaction examplesThe standardized protocol made blockchain data integration trivial—just POST requests to get formatted, AI-ready dataMulti-chain support means explanations can reference actual activity across different networksBase IntegrationLow gas costs made badge minting practical for educational use casesFast transaction finality provides immediate feedback for quiz completionStrong ecosystem support for NFT tooling and wallet integrationNotable Technical InnovationsAdaptive Explanation Engine The system maintains separate knowledge states for each user. When explaining new concepts, it queries the user's MeTTa graph to determine what they already know, then generates contextually appropriate explanations. A beginner gets "DeFi is decentralized finance," while someone who already knows DeFi basics gets "DeFi protocols like Aave use over-collateralization to manage lending risk."Live Transaction Context Instead of static examples, every explanation can include real, recent blockchain activity. The agent queries Blockscout MCP with extracted concepts and surfaces relevant transactions, making abstract concepts tangible.Quiz-Gated NFT Minting The smart contract integration was particularly elegant—quiz questions are generated by ASI:One based on the user's captured knowledge graph, ensuring personalized difficulty. Only after proving understanding (80%+ score) can users mint domain-specific badges.Cross-Extension Learning Persistence The knowledge graph persists across browser sessions and websites. A user can learn about "yield farming" on one site, then see that knowledge referenced when they encounter "liquidity mining" elsewhere.Agent-Extension Communication The browser extension communicates with a local agent that's simultaneously registered on Agentverse, enabling both private learning and potential collaborative features with other agents in the ecosystem.