
Bright Data Market Intelligence Agent is an autonomous AI system that delivers real-time competitive intelligence across three domains: GTM (Go-To-Market) intelligence, finance & market pricing analysis, and security & compliance monitoring. Powered by Gemini 2.5 Flash and backed by Bright Data's SERP API, Web Unlocker, and Scraper API templates, the agent autonomously scrapes live data from 9+ platforms including Amazon, eBay, Tokopedia, Shopee, Lazada, Walmart, and more — then synthesizes structured intelligence reports in seconds. Key capabilities include multi-platform price comparison with USD/IDR normalization, competitor research with hiring velocity signals, vendor risk scoring, brand exposure scanning, threat intelligence monitoring, and regulatory compliance tracking. Track 3 adds real-time open-web threat detection, leaked credential scanning, third-party vendor risk assessment, and compliance change monitoring across jurisdictions. The system features automatic Gemini API key rotation with AI/ML API and Groq fallback to ensure 24/7 availability. Built for the lablab.ai × Bright Data Web Data UNLOCKED Hackathon, May 2026
31 May 2026

BriefAI is an autonomous AI agent built to solve one of the most overlooked productivity problems in enterprise environments: the time wasted on repetitive document preparation. Managers, HR professionals, and sales teams spend 30 to 60 minutes crafting briefs that follow the same structure every time. BriefAI eliminates that friction entirely. Users simply select one of five enterprise brief types — Meeting Brief, Project Kickoff Brief, Client Proposal Draft, Interview Prep Sheet, or SOP Generator — fill in a short context-aware form, and receive a fully structured, professional document in seconds, powered by Google Gemini 2.5 Flash. The application is built on Next.js 14 with TypeScript, deployed on Vercel, and features a clean dark-themed UI designed for professional use. Each brief type has its own tailored prompt engineering logic, ensuring the output is not just generic text but a truly actionable enterprise document. BriefAI was built as a solo project for the AI Agent Olympics Hackathon at Milan AI Week 2026, competing in the Enterprise Utility track. It targets a real-world pain point experienced daily by thousands of professionals, and demonstrates how a focused AI agent — with the right prompt design — can deliver immediate, measurable value without complex infrastructure. Live demo: https://briefai-enterprise.vercel.app
19 May 2026

Conversa AI is an enterprise-grade AI agent platform designed to solve two critical challenges in modern business: unstructured document processing and data accessibility. The first feature, OCR Docs, allows users to upload PDF or image files (JPEG, PNG, WEBP, HEIC, HEIF). Gemini Vision API extracts the full content — including text, tables, and key fields such as invoice numbers, dates, and contract values — and returns structured JSON. For scanned documents, Conversa AI automatically switches to a page-by-page OCR fallback strategy, rendering each page as a high-resolution PNG before sending it to Gemini for text extraction. Users can then chat with their documents using natural language questions. The second feature, Data Intelligence, enables users to upload CSV or Excel files. All sheets are parsed simultaneously using SheetJS, then passed to Gemini with full conversation history for multi-turn analysis. Users can ask questions like "What is the total revenue this quarter?" or "Are there any anomalies in this dataset?" and receive accurate, data-grounded answers in real time with word-by-word streaming responses. Both features include a 3x retry mechanism with exponential backoff (2s, 4s, 8s) to handle Gemini API rate limits gracefully. The application is fully deployed on Vercel with serverless API routes, a 60-second execution limit for heavy OCR tasks, and a single GEMINI_API_KEY environment variable for configuration. Live demo: https://conversa-ocr-docs.vercel.app GitHub: https://github.com/jefribulomakassar/conversa-ocr-docs
19 May 2026

Conversa AI MCP Server bridges IBM Bob IDE with powerful AI capabilities through the Model Context Protocol (MCP). Instead of switching between tools, developers can now invoke AI-powered features directly from Bob Shell using natural language. The server exposes 5 production-ready MCP tools: - conversa_analyze_data: AI-powered analysis of CSV, JSON, and text data with trend insights - conversa_scan_document: OCR extraction from document URLs including KTP, certificates, and invoices - conversa_build_form: Generate complete form schemas from natural language descriptions - conversa_scrape_url: Extract structured content from any web URL in markdown format - conversa_deploy_code: Commit files to GitHub and trigger Vercel deployment in one command Built with Next.js 14 and TypeScript, deployed on Vercel, the server implements JSON-RPC 2.0 over HTTP and SSE transport — fully compatible with IBM Bob Shell's MCP client. AI capabilities are powered by Gemini 2.0 Flash for OCR and analysis, with GitHub REST API and Vercel API for deployment automation. IBM Bob was used as the primary development partner throughout the entire build — analyzing repository structure, adding error handling and Zod input validation across all tools, and rewriting documentation. All Bob sessions are exported and committed to the repository as proof of usage. This project demonstrates how AI agents can live inside the developer's workflow rather than existing as separate tools — reducing context switching and accelerating development velocity
17 May 2026