Custom software engineering and AI services
Procyon Research is a new type of software consultancy based in Southern California which hybridizes human insight with machine intelligence to deliver software, applied AI, and system design more quickly and at a higher state of quality than previously possible with older methodologies.
Whole products built from an empty repository: web apps, APIs, device software, and the cloud infrastructure underneath. Procyon takes an idea through architecture, build-out, and launch, then hands your team the keys to a system it can run and grow on its own.
Product Architecture / Full-Stack Builds / Cloud Infrastructure / Launch
Systems built around large language models: knowledge management, product oracles that know your product cold, chat bots, and content generation. Each ships with the retrieval and evaluation plumbing underneath.
LLM Orchestration / RAG / Agents / Evals
Hard as it is to believe, many problems are still best solved with traditional machine learning: no slow, expensive LLM required. Classifiers, forecasters, and anomaly detectors that run in milliseconds on hardware you already own.
Classification / Forecasting / Anomaly Detection / Recommendation
Legacy codebases ported to new languages and architectures, with inputs and outputs validated against the original at every step so behavior survives the move. Then the extensions: cleaner interfaces, test coverage where there was none, new capability layered onto software you already rely on.
Incremental Migration / Behavioral Validation / Test Harnesses / API Design
Digging into the shape of your data to find what is buried in it: profiling, exploratory analysis, and the unglamorous cleaning that real answers depend on. When a one-off analysis needs to become routine, it gets a custom transformation pipeline built around it.
Exploratory Analysis / Data Cleaning / Transformation Pipelines / Reporting
Vibe-coded messes untangled, no judgement. When AI-generated code has grown past what anyone can safely change, the job is to work out what it actually does, pin that down with tests, and restructure it so people - and their agents - can build on it again.
Code Archaeology / Test Coverage / Refactoring / Documentation
Software for hardware: embedded firmware, motion control, sensor fusion, and the device-to-cloud plumbing in between. The work reaches down to the timing-and-interrupts level and up to the fleet dashboard, including the models that run on-device.
Embedded C / RTOS / Sensor Fusion / Edge Inference
Every engagement, three commitments.
What the system is supposed to do gets written down as tests, run against real data, and proven again on every change. Correctness is demonstrated, never assumed.
Inputs go bad, networks drop, hardware dies. Systems here expect that: they degrade gracefully, recover on their own, and say plainly what went wrong.
The simplest design that solves the problem, with clean seams where the next capability will attach. Your team can extend it without a rewrite.
Describe the system you need, or the problem you need solved.