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 Claude, GPT, and locally running Ollama models into a native macOS desktop app. Requests switch between cloud and local models without context loss — history is model-agnostic, sensitive content can stay on-device. In production since early 2026, written in TypeScript on Electron, stored in local SQLite.
DocMind — RAG Frontend for Private Data
DocMind makes private document collections — PDFs, notes, internal wikis, contract archives — semantically searchable, fully offline. Embeddings are computed locally, Qdrant runs as a sidecar process inside the Electron app. User data does not leave the computer. Built for lawyers, fiduciaries, research teams, and SME leadership who need AI on confidential material without sending it to the cloud.
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 Harrier embeddings, provides the research base for our blog articles, and connects via an MCP server to Claude Code, Mingly, and our internal tools. Single source of truth for every advisory sparring session.
Prüfstand — AI Testing Framework
Prüfstand is our test bench for software and AI projects: thirteen specialised agents covering security (SAST, dependency and secret scanning, OWASP), code quality and accessibility, function (unit, E2E, API), load, plus macOS signing and notarisation. An LLM selects the agents that fit a given target, classifies the findings and compiles them into a report. As of July 2026 it is an internal prototype — no CI integration and no customer deployment yet.
Nexbid — Open Infrastructure for Agentic Commerce
Nexbid is a two-sided marketplace for the moment AI agents buy: publishers bring content, advertisers bring products and campaigns, Nexbid connects both sides through open protocols (AdCP, MCP) instead of a walled garden. Live since April 2026 with discovery API, MCP server, 19 transaction tools, x402 payment rail, and wallet-pay magic-link. Founding publisher Betty Bossi, founding advertisers FOCUSWATER and The Champagne.
Compass — Research Project
Compass is our internal research project on agentic workflows for complex research tasks: translate multi-step work that a human would spread over days into an orchestrated agent flow — with control checkpoints, source provenance, and auditable reasoning. Written in Python on the Claude Agent SDK, with MCP-based tool connections to our internal knowledge sources.
Eval-Framework — LLM-as-a-Judge with bias correction
Our framework for systematic evaluation of LLM outputs: pairwise comparisons, bias corrections (position swap, verbosity, self-preference), calibration against a human reference rating with Spearman ρ as the acceptance threshold. As of July 2026: developed internally and calibrated once, in March 2026. It does not yet run as a standing quality gate and has not been used in a customer mandate.
Mineralis — AI-native Equity Research for Mining Equities
Mineralis is a SaaS platform for investment research in the global mining and energy market: every listed mining company in the world gets a self-updating AI research profile with source attribution, material events are detected and classified in real time, and an explainable scoring framework (MAS-Score) replaces black-box DCF. Positioned as 'Bloomberg for junior miners' — the depth and coverage of CapIQ/S&P (USD 30K/year) with AI-first architecture and transparent pricing.
Marketing Mix Modeling — measuring impact with Google Meridian
A multi-tenant platform for agencies and brands to measure which channel actually caused revenue — not who clicked last. It builds on Google Meridian, the openly published Bayesian MMM framework. Connectors consolidate media data from Google Ads, Meta, LinkedIn, DV360 and GA4 at weekly granularity; modelling and analysis run in the Google Cloud Zurich region.
Swiss Gazette — the Swiss commercial gazette, searchable in four languages
The Swiss Official Gazette of Commerce publishes official notices daily — commercial register, debt collection, bankruptcies. Officially available is not the same as usable: publications appear individually, are hard to filter, and come in different languages depending on the canton. Swiss Gazette turns that into a searchable, four-language interface with a canton filter. Live at swissgazette.com.
Expat calculator — affordability and Lex Koller for newcomers
Foreign nationals wanting to buy residential property in Switzerland hit two hurdles at once: the banks' affordability rules and the authorisation requirement under Lex Koller. Both are documented separately and hard for newcomers to combine. The calculator answers both in a step wizard — no account, with a PDF to take away.
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.
Voice of the Customer — Feedback Pipeline for a Swiss Wholesaler
A Swiss wholesaler collects customer feedback across several touchpoints but evaluated it largely by hand. We built the pipeline that runs from raw feedback to a classified metric: export from the survey system, AI-assisted classification, database, reporting views, dashboard. The engagement is ordered in stages, and the code transfers to the client at the end.
A Typical Enquiry — Internal Enquiry Desk, from Idea to Assessment
This is how enquiries reach us: already phrased as a solution. This entry stands for a type of request we see regularly — an organisation holds expertise that has grown over years in internal stores, and wants a chatbot on top of it. Here it was a Swiss research institution with a specialist enquiry desk. What follows is our method: which questions we ask first, why a RAG system did turn out to fit, and where we contradicted the client.