Nomograph Labs builds instruments that help people leverage AI for long-running, structured work: context engineering, spec management, reproducible benchmarking.
What we focus on
Most AI tooling optimizes for single-turn tasks. We're interested in the harder problem: multi-session work across large codebases, formal engineering artifacts, and collaborative projects where context outlives any single conversation. The tools we build address three layers of that problem.
Context engineering
How you present information to an AI matters more than how you retrieve it. Our benchmarks consistently show this. We build tools that make structured artifacts legible to AI through composable CLI commands and MCP servers.
Spec management
Long-running work needs structure that persists across sessions. Synthesist tracks specs, task dependencies, stakeholder dispositions, and propagation chains. The human and the agent use the same interface.
Reproducible evaluation
Claims about AI performance need measurement. Our benchmarks are designed for independent replication: open tasks, open data, structured scoring, statistical frameworks.
How this started
This began as an academic exploration of how AI interacts with structured engineering artifacts. We built a tree-sitter grammar for SysML v2, then a CLI tool, then a benchmark harness to measure whether the tool actually helped. Each step produced something others could use and something we could measure.
Along the way we found alignment with GitLab's Knowledge Graph team, who are solving related problems in context engineering and retrieval at production scale. That collaboration has been productive: our research on prescriptive failure patterns and tool description effectiveness grew out of working with their eval framework.
The methodology is to build evaluation apparatus and look for where high-leverage AI use can be discovered. Model-based systems engineering is an area we think has enormous potential: the industries that heavily adopt MBSE (defense, aerospace, automotive, medical devices) are typically slower to adopt modern AI tooling. We'd like to help them get there through open instrumentation and foster a community around LLM-mediated experimentation and engineering.
The name
A nomograph is a graphical calculation instrument. Three parallel scales, each graduated differently. An isopleth -- a line laid across the scales -- reads the answer by alignment. No computation. The structure of the instrument encodes the equation.
Our mark is an isopleth crossing three scales. Each scale has its own graduation rhythm. The curve reads from top-left to bottom-right. The N emerges from the reading.
