Last updated: 3 September 2026

MIHOS carries the swiss made software + AI label. AI is the core technology of the product, not an added feature: without it MIHOS does not function. The application is designed, developed and operated in Switzerland by MUUM Sarl, in Nyon. The AI models it runs on are third party and they are not Swiss made. What is Swiss made is everything built around them: the capture application, the consent layer, the scoring engine, the playbook logic and the CRM write-back.

Hosting

MIHOS is a SaaS platform. Recordings, transcripts and account data are stored in Switzerland. Speech to text and speaker separation are performed by Gladia, a French provider, consumed as a hosted API and running inside the European Union. Model inference runs on European infrastructure operated by OVHcloud.

Level

We build on foundation models consumed as a service and wrap them in our own layer: orchestration, the playbook context, the scoring engine, the coaching logic and the CRM write-back. The models are a component of the application, not a system we operate ourselves.

AI technologies used

Automatic speech recognition, speaker diarisation, and large language models for analysis, scoring and coaching text.

Model origin and type

Established commercial closed source models, consumed as delivered through secured APIs. We operate no proprietary foundation model and we run no model on our own hardware.

Customisation and fine tuning

We do not train and we do not fine tune any model. Behaviour is steered through prompts, retrieval and your own playbook context. Meeting content is never used to train a model, ours or a provider's. MIHOS does get better with use, but at the application layer: the product accumulates your playbook, your real objections and the outcome of your deals, and feeds them back as context. The models themselves never change.

What the AI is not allowed to do

No emotion inference. The sentiment and emotion detection features our providers offer are switched off in our pipeline. No voiceprint: MIHOS does not build a template that would let the same voice be recognised from one meeting to the next. No inference of special category data from a voice or a transcript. Scores and recommendations are indicative and AI output can be wrong: every decision about a person involves human judgement, every write into a customer system is logged and reversible, and every score is traceable back to the timestamped passage that produced it.