Cases
What we build and who we advise — practice, not PowerPoint.
Own developments
Our own AI systems as proof: we know what we're talking about.
Mingly — Multi-LLM Desktop App
Mingly brings multiple AI models (Claude, GPT, local Ollama models) into a native macOS desktop app. In production since early 2026, with focus on privacy and multi-model routing.
DocMind — RAG Frontend for Private Data
DocMind is a desktop application that makes private document collections (PDFs, notes, wikis) searchable — fully offline, with locally running embeddings and Qdrant as vector store.
RAG-Wissen — Production RAG for our own knowledge base
RAG-Wissen is our internal RAG system for advisory knowledge, technical documentation, and market intelligence. Runs in production with Qdrant v1.17.1 and provides the research base for our blog articles.
Prüfstand — AI Testing Framework
Prüfstand is our framework for systematic testing of AI systems — prompt variations, model comparisons, quality scoring via LLM-as-a-Judge. Used for quality assurance of our own products.
Nexbid — Agentic Ad Server
Nexbid is a platform for agent commerce: advertising that AI agents can understand, evaluate, and transact with. Live with x402 payment pilot, MCP server, and AdCP 3.0 trust surface.
Compass — Research Project
Compass is an internal research project investigating agentic workflows in complex research tasks.
Eval-Framework — LLM-as-a-Judge
Our framework for systematic evaluation of LLM outputs — with pairwise comparisons, bias corrections, and calibration against human baselines.
Customer cases
Advisory engagements where we've supported clients.
Automated Document Processing with AI
A Swiss mid-market company processed thousands of incoming documents per month — invoices, contracts, delivery notes — manually by a clerical team. We designed an AI pipeline for classification and data extraction, evaluated vendors, and accompanied the rollout.
AI-Supported Customer Service Optimization
A Swiss service provider with high customer-service inquiry volume wanted to raise first-contact-resolution while cutting response times. We designed an AI-supported workflow for incoming inquiries — classification, draft responses, FAQ bot — and accompanied the rollout with the service team.
Individual AI Strategy Advisory for Leadership
The leadership team of a Swiss company wanted to prioritise AI investments strategically rather than scatter them opportunistically into one-off projects. In a focused series of discovery sessions we identified use cases, weighted them, and translated them into a 12-month roadmap.