Work

For companies

  • 01

    Agentic systems

    Multi-step agents with tool access to existing systems, schema-validated and traceable in the audit log.

  • 02

    Knowledge systems

    Hybrid retrieval with source citations and a permission filter on every chunk.

  • 03

    Model adaptation

    Fine-tuning open models on domain language, forms and standards.

  • 04

    Image and sensor data

    Deep learning for image, 3D and measurement data, from classification to segmentation.

Work in detail →

Lab

Our own systems

The CSV explorer built by the coding agent, with two filters and exported rows
coding agent · built from one prompt · recording (74 s) in the Lab
robotics · given a name, it finds the object · physics simulation · objects: YCB, fixtures: RoboCasa/NVIDIA (CC BY 4.0)
Interface of the validation layer: query with line 7 marked and the finding timespan_without_unit
SIEM validation layer · one error in line 7 that the parser accepts
TippelPi interface: one question in German to the brew log, the answer with the cited passages as sources
TippelPi · answer from a test document, with sources

Lab in detail →

About Tippel

AI engineering from Hombressen

Tippel is an owner-managed AI engineering company. It was founded by Lukas Friedrich, a physicist specialising in deep learning. The standard for every project comes from research: a result only counts once it is measured and reproducible. Every project stays transferable from the first week, because source code, documentation and the deployment description live in the client’s repositories.

About Tippel →

LeadLukas Friedrich
LocationHombressen near Kassel, Germany
Deploymentcloud API · EU cloud · your own servers
Contactinfo@tippel.ai