.png&w=256&q=75)
2
2
Italy
6+ years of experience
I am a Data and AI Engineer based in Italy with experience in Python, Django, SQL, data engineering, LLM evaluation, and AI-powered developer workflows. I have worked on backend systems, IoT data platforms, ETL pipelines, software testing, and AI evaluation tasks. For this hackathon, I am interested in building practical developer tools that help teams understand codebases faster, generate better documentation, improve testing, and reduce repetitive engineering work using IBM Bob.

MenuTaste is a web-based enterprise AI agent for food entrepreneurs, cafes, restaurants, and small food businesses. It helps users turn a food or drink idea into a structured product-quality, nutrition, risk, market-fit, and launch-readiness report. The user enters a product name, ingredients, business type, location, customer segment, dietary focus, target price, and preparation complexity. MenuTaste then runs a multi-step workflow: it performs local ingredient and nutrition-signal analysis, detects allergens and dietary conflicts, scores the product across nutrition, quality, market fit, and operations, and sends a structured prompt to a Featherless open-source model for deeper business reasoning. The final output includes an executive summary, nutrition estimate, risk review, ingredient notes, Featherless AI reasoning, recommended actions, launch checklist, and downloadable Markdown and JSON reports. This makes MenuTaste useful for early-stage restaurants and food entrepreneurs who need to validate a menu item before piloting it with customers. The system combines deterministic local scoring with Featherless AI reasoning. This hybrid design keeps core food-risk checks explainable while using open-source LLM inference for strategy, recommendations, customer positioning, and launch planning. The app is designed as a production-style Streamlit web application and deployed on Vultr for the hackathon demo.
19 May 2026

MenuNest: AI Copilot for Food Entrepreneurs is an AI-powered Streamlit web app that helps food founders move from a rough food business idea to a practical launch plan. Many early-stage food entrepreneurs have recipes, cultural food concepts, or local market ideas, but they often struggle with menu planning, pricing, ingredient organization, allergens, marketing, and launch validation. MenuNest solves this by turning a simple concept into a structured business launch package. Users enter their food idea, business type, cuisine, location, budget, target customers, dietary focus, launch goal, and output language. The app then generates a launch dashboard, business overview, menu and pricing suggestions, ingredient and allergen notes, customer personas, marketing content, launch checklist, and exportable Markdown or JSON reports. The app works reliably in demo mode without API keys and also supports configurable AI provider modes for IBM watsonx.ai, OpenAI, and Anthropic. The first demo focuses on small and cultural food businesses in Italy and Europe, such as cafes, kiosks, bakeries, catering services, food trucks, home chefs, and restaurants. IBM Bob was used as the development partner for workflow design, repository cleanup, Streamlit UI improvements, prompt/schema design, provider configuration, debugging, tests, and final reliability checks. The final test suite passed 164 tests, covering demo mode, validation, dynamic business idea behavior, language support, exports, and multi-provider integration.
17 May 2026