Tanner Lab GmbH

AI Engineering

Custom AI Systems

We build custom AI systems and AI agents that understand documents, work with your company data, and reliably reduce recurring work - integrated into the software you already run.

  • From idea to production integration and ongoing development.
  • Not yet sure where AI helps? We assess: build now or redesign first.
AI Engineering

Location, Hosting & Memberships

Made in Switzerland · Swiss, EU, or global hosting options · Member of Swico & swissICT

AI Idea Check

CHF 190 · fixed price

You describe your problem or AI idea in a call, in your own words. We assess what actually holds up technically and deliver a clear written recommendation.

How would we sensibly solve this with AI?

How it works

  1. The call

    By phone or video. You describe the problem, context, and systems in your own words; we ask the questions that matter. No preparation needed, documents and examples are welcome.

  2. Technical assessment

    We research with focus and assess what actually holds up technically in your case, and where AI delivers the most value.

  3. Afterwards

    You get a concise written recommendation with one solution approach and the smallest sensible first step.

What you get

One page, in writing:

  • A clear assessment of what AI can do in your case
  • One recommended solution approach, not a list of options
  • The smallest sensible first step

Request an AI Idea Check

Leave your contact details. We come back with slots for the call. Fixed price CHF 190, implementation not included.

We process the information you submit as described in our privacy policy.

Portrait of Marc Besson

Client testimonial

“The collaboration with Tanner Lab and eventlokale.ch was outstanding. Their ability to visualize entropy and consistently reduce it is particularly impressive. They are highly skilled, clearly structured, focused, and at the same time dynamic and flexible. Problems are addressed directly and solved in a solution-oriented manner. It is a partnership that creates order and enables real progress. - Simply outstanding!”

Marc Besson

Managing Director, Eventlokale.ch

What we build

We automate clearly scoped tasks and workflows where AI can reliably create value using your data and systems.

Message triage

Classify incoming messages (support, sales, internal) and route them or draft a prepared response. Humans approve before sending.

AI-drafted replies with context

Draft emails or chat replies that pull context from your CRM, ticketing, or internal knowledge. A human reviews and sends. Saves real time on repetitive correspondence.

Document OCR with vision models

Digitise documents reliably using modern Vision-Language Models. Far better than legacy OCR on real-world inputs: scans, photos, mixed layouts, handwriting.

Cross-system Q&A

Answer targeted, well-scoped questions by pulling from multiple systems (CRM, accounting, SaaS databases, internal docs). RAG done properly, with citations.

Agentic RAG

Agentic RAG combines retrieval, tool use, and multi-step reasoning. Useful when a system needs to search your knowledge, call APIs, compare sources, and return cited answers.

Workflow automation with AI in the loop

Multi-step business processes (read invoice, extract fields, match to PO, route for approval) with AI handling the fuzzy parts and humans approving the consequential steps.

Tell us about your AI project

Describe your idea or recurring workload. We will respond with a pragmatic next step.

We process the information you submit as described in our privacy policy.

Selected Projects

NT Group - Industrial AI: RAG for Spare Part Identification

Tanner Lab delivered the RAG/LLM component: multimodal knowledge retrieval to match a photo to the right technical documentation. The overall PoC was developed in collaboration with Hatimeria.

eventlokale.ch - Production Automation

Automation designed, implemented, and deployed to production, complemented by advisory work on digital product development and further processes.

Methodologies

In recent years, the term AI Engineering has become established. It means combining machine learning engineering and software development: practical, applied AI where AI technologies are integrated into real IT systems and business processes.

What AI actually is

Artificial Intelligence is not magic. It is a set of techniques that allow computers to learn from data and make predictions or decisions.

  • AI systems learn patterns from data and can also follow explicit rules
  • They excel at tasks with clear patterns: classification, prediction, and optimization
  • They require quality data, clear objectives, and ongoing maintenance

Generative AI vs. Traditional AI

The AI landscape has different branches, each valuable for different purposes.

Traditional AI & Machine Learning

Trained on your business data to make predictions, classify information, or optimize processes.

Examples: Spam filtering, fraud detection, text and image classification, recommendation systems, etc.

Generative AI

Large language models and similar systems that can understand context, generate content, and interact naturally.

Examples: Search systems, chatbots, agents, text and code generation, and more

Tell us about your AI project

Describe your idea or recurring workload. We will respond with a pragmatic next step.