Solara28
Founder & Chief Architect — Enterprise multi-tenant AI-native SaaS commerce platform
Jun 2025 – Apr 2026 · Zurich · Venture built and transitioned to production readiness. Work completed; Solara28 is now managed by his wife.
6M+Lines of production code delivered single-handedly with 32 AI agents in 8 teams
300+Business functions in an AI-native multi-tenant commerce platform
Open sourcePublished the Buonaiuto-Doc4LLM MCP server
Skills usedAI governance, risk & regulatory complianceMachine learning, deep learning & MLOpsData Strategy for AIGenerative AI & LLM solutionsAgentic AI & AI-native engineeringSolution & enterprise architectureData architecture, engineering & governanceCloud & multi-tenant SaaS platformsTeam leadership & talent developmentBusiness value & financial managementEntrepreneurship & venture buildingDigital marketing & customer analyticsProduct & full-stack engineering
All 24 contributions
Venture & market positioning
- Founded, ideated, architected and single-handedly developed Solara28, an AI-native multi-tenant SaaS platform for European commerce verticals — food services, restaurants, pharmacies, grocery retailers, wine and spirits, catering, coffee shops and event ticketing — positioned under the vision “Illuminate your commerce” as a local-first, zero-commission alternative to global marketplace aggregators and platforms such as Amazon, Shopify, Just Eat, Deliveroo, PrestaShop and WooCommerce. Evidence ↗
- Designed as next-generation commerce infrastructure for local economies, combining AI-native operations, multi-tenant SaaS architecture and decentralised business ownership to support European business sovereignty and restore data sovereignty, margin control and customer ownership to independent merchants.
- Designed a sustainable, zero-commission commerce model enabling independent B2C ecosystems, in which merchants retain full ownership of customer, order and product data while improving long-term profitability.
- Engineered Solara28 as a high-performance, AI-powered match for global marketplace incumbents on enterprise capability, while preserving local control, regulatory compliance and economic value distribution for independent merchants.
- Developed an ecosystem strategy covering payments, accounting and e-invoicing, logistics, local commerce associations, digital agencies and technology providers to accelerate merchant acquisition and operational integration.
- Produced promotional videos with AI video generation (Seedance 2.5 in Dreamina).
Agentic Factory & AI-native engineering
- Architected and implemented a governed Agentic Factory coordinating eight specialised virtual teams and 32 autonomous AI agents across the end-to-end software delivery lifecycle, generating 6,000,000+ lines of production-ready code, documentation and change artefacts in under one year across a polyglot stack (TypeScript, Supabase/PostgreSQL, FastAPI, Stripe, Vercel).
- An audited codebase review (August 2026) across eight engineering roles — frontend, backend, database, QA/security, DevOps, localisation, architecture and documentation — estimated the work at about 274.8 person-years (60,462 working days), roughly 275 engineers for one year, with a salary-equivalent labour value of about CHF 30.1M / EUR 19.6M at the midpoint (range CHF 25.9M–34.3M / EUR 15.5M–23.7M); all of it was delivered single-handedly. Evidence ↗
- Established an end-to-end autonomous AI delivery model covering architecture design, code generation, testing, security validation, cloud implementation and documentation, with every artefact traceable to requirements, architecture decisions, source-control changes, code review, automated testing, security scanning and release approval; the Agentic Factory executed work across engineering, QA, DevOps, compliance, localisation, marketing, branding, e-commerce and online payments.
- Established Solara28 as a large-scale reference implementation of Agentic AI product engineering, demonstrating the viability of autonomous multi-agent systems in enterprise-grade software delivery.
- Governed the automated delivery lifecycle — architecture, software engineering, testing, security, DevOps and documentation — as an agentic AI operating model aligned with the EU AI Act.
- Designed, built and published the open-source Buonaiuto-Doc4LLM MCP server, which auto-detects a project’s library stack, fetches current official documentation and serves it version-aware to AI coding assistants — the RAG infrastructure that kept the agents’ 6M+ lines of code aligned with current, secure architectural standards and eliminated API hallucinations.
Applied Generative AI
- Architected a provider-agnostic LLM service layer (TypeScript/Node.js/Supabase) connecting OpenAI, Anthropic and Gemini APIs, with configurable provider settings, prompt governance, conversation logging and health monitoring, powering conversational and voice-enabled commerce (“Talk to Your Shop”), automated catalogue ingestion from PDFs, photos and Excel, and predictive revenue forecasting.
- Embedded operational AI directly into the commerce execution layer: one-click PDF-to-live-store catalogue imports, natural-language conversational assistants, voice-enabled customer ordering via chatbots, a Merchant AI Assistant and predictive CRM analytics built natively into the platform.
Platform architecture & governance
- Architected the platform so merchants retain full ownership of all operational and customer data, with a GDPR-native multi-tenant architecture for the European market, automated audit trails and European data residency.
- Delivered mobile-first, WCAG-accessible experiences in five languages from day one — Italian, English, German, French and Spanish — with theme-based templates for 9+ store verticals, including restaurant ingredient customisation, pharmacy prescription workflows and event ticketing with QR check-in.
- Engineered a secure PostgreSQL architecture with hundreds of tables and compound Row Level Security policies, enforcing deterministic tenant isolation across platform, store, staff and customer contexts, with governance-by-design audit logging, activity feeds and observability of API latency, background jobs, errors and cache performance.
- Built a polyglot, high-performance stack on TypeScript, Supabase/PostgreSQL, FastAPI and Apache Spark, supporting real-time operations, analytics and scalable AI workloads.
- Moved Solara28 from architecture and development into controlled production readiness, including security hardening, environment separation, release governance, monitoring, backup and recovery procedures and operational support processes.
Commerce capabilities
- Delivered 300+ discrete business functions across platform and store contexts, including product catalogue management with customisers, multi-step checkout, order lifecycle management, delivery-zone configuration, driver assignment, workforce logistics, automated SDI e-invoicing and support/ticketing workflows.
- Designed a fully API-first commerce infrastructure governing the complete retail lifecycle — dynamic catalogue management, logistics and proprietary driver-network routing, native multi-channel CRM and loyalty analytics — enabling modular extensibility and third-party integrations.
- Built the platform administration domain: store onboarding and lifecycle, subscriptions and seat management, permission templates, monitoring dashboards, feature flags, audit and operational tooling, cross-store analytics, and billing with SDI e-invoicing for Italy.
- Built the store operations domain: catalogue and category management, order lifecycle and control centre, delivery operations and driver management, reviews moderation, reporting and analytics, theme and branding configuration, and staff management including bulk import.
- Implemented automated loyalty management (points, tiers, rewards) and RFM-driven customer insights integrated with CRM workflows, email marketing automation and customer intelligence to support retention and repeat purchasing.