Treatment response from H&E biopsy scans
We built the AI and ML pipeline that trains a model on H&E-stained cancer biopsy scans to predict a patient’s chance of responding to treatment.
Read the case study
From boardroom to production. We design, build, and ship AI-native products and automations.

Market entry, AI roadmaps, and the structure and operating model for new ventures and joint ventures.

From the first use case to agents running in your production systems, with the evaluation built before the deployment.

Custom models, data pipelines and LLM applications, built so every result can be validated and every run repeated.
We built the AI and ML pipeline that trains a model on H&E-stained cancer biopsy scans to predict a patient’s chance of responding to treatment.
Read the case study
We designed the setup and the concept for a joint venture in health real-world-data research, covering structure, scope and operating model.
Read the case study
We built the control plane that runs coding agents against real repositories as durable, sandboxed, reviewable work — and we run our own delivery on it.
Read the case study
We defined and built a dance-course platform end to end — product design, information architecture, mobile app, admin, API and infrastructure — replacing an earlier prototype entirely.
Read the case study
Femy is our own app for hormones, menopause and longevity. Its editorial standard is enforced by the build: an article without enough dated, resolvable sources does not compile.
Read the case study
We designed the venture concept for a computational drug-discovery service and trained the model underneath it — a repurposing pipeline that has to re-find known medicine before its novel output counts.
Read the case study
A system that takes a technical problem and returns an invention brief whose every claim is cited — with a prior-art search and a critic loop standing between the idea and the output.
Read the case study
A structured fourteen-day venture-validation sprint, redesigned so a conversational agent runs the method with the founder instead of handing them a workbook.
Read the case study
Marcado Studios is founder-led from Berlin. The team is small on purpose, extended by senior specialists where a project needs them, and the person who answers your first mail stays on the project.
About usThree things: AI strategy and agent deployment, machine-learning and LLM engineering, and strategy consulting including venture and joint-venture design. All three are done by the same small team.
Mid-size companies in the German-speaking market, and occasionally well-funded startups. We take on few projects at once, which is the trade-off for the team staying small.
Project-based, on a daily rate, with a scope we agree in writing before we start. We are happy to talk through the shape of it in a first call at no cost.
Write to [email protected] and describe the problem in a paragraph. A person answers. If you prefer a form, the contact page has one.
Both, and mostly build. Two client case studies and five of our own apps in the App Store are on the Work page.
Yes. We are based in Berlin and work in German and English, remote-first, with clients across the DACH region and beyond.
Still have questions? Get in touch