JEGJonas El Gammal
Beyond the research portfolio

Projects

Companies and technical experiments that turn data, automation, and machine intelligence into usable systems.

Company · Co-founder, Managing Director & CTO

An integrated data and automation platform for medical practices in Germany.

Bright Interface GmbH is building the connective layer that many practices currently lack: a system that assimilates fragmented operational data and turns it into coordinated services for patients, medical teams, and practice management. The aim is not to automate clinical judgement, but to make the surrounding workflows more accessible, reliable, and efficient.

01

For patients

Online booking, voice-assisted routine interactions, reminders, delay notifications, self check-in, and proactive invitations for vaccinations and check-ups.

02

For medical teams

Less administrative overhead through better scheduling, documentation support, task tracking, and connected workflows.

03

For practices

Operational visibility across appointment duration, room utilisation, capacity, and management KPIs through a unified dashboard.

My role

As co-founder, Managing Director and CTO, I lead product and technical strategy, system architecture, engineering quality, data integration, applied AI, and technical delivery.

Active experiment

Graphsmith

An AI-native planning and execution system built around typed graph programs.

Graphsmith planning, compilation and execution pipeline

Language models are good at semantic intent but unreliable at emitting large executable structures directly. Graphsmith separates these jobs: a model proposes a typed intermediate plan, while deterministic machinery compiles, validates, repairs, executes and traces the graph.

Current direction

The project explores guarded execution, loop lowering, local repair, reusable skills, trace-derived promotion signals, and trust-aware remote reuse. Its central bet is that inspectable graph structure gives models—and people—a better substrate for understanding and repairing programs than opaque one-shot generation.

View Graphsmith on GitHub