JEGJonas El Gammal
Typed graph planning and execution

Reliable AI systems

Graphsmith explores how language models can plan executable programs without also being responsible for their structural correctness.

Graphsmith planning, compilation, repair, and execution pipeline

Semantic planning, compiled

Language models often produce workflows that look plausible but contain missing bindings, invalid control flow, or invented capabilities. Graphsmith gives the model a narrower job: propose semantic intent in a typed intermediate representation. Deterministic machinery then compiles that representation into a graph, validates contracts and control flow, executes it, and records a node-level trace.

The current prototype supports guarded branches, bounded loops, local structural repair, and reusable skills drawn from local or remote registries. When execution exposes a bounded capability gap, the system can generate and validate a missing skill before re-entering the planning loop. Provenance and traces remain attached so that successful structure can be inspected and considered for reuse rather than disappearing inside a single model response.

Current questions

This is an experimental AI-systems project, not yet a general-purpose programming environment. Its capability boundary is deliberate: arbitrary code synthesis and reliable multi-region repair remain open problems. Explore the source code.