Labs
We build before we advise
Active projects where we test architecture decisions, benchmark real hardware, and publish what we learn. These inform our solutions and our product thinking.
Governed AI Routing Pipeline
How do you route enterprise prompts to the right model without sending PII to the cloud? We built a rules-first router with statistical PII detection and SLM fallback. Three domains (healthcare, finance, telecom), 60 synthetic prompts, full audit trail.
Published findings
This work is part of our exploration while building neurelay.ai, an AI governance platform for enterprise tool access control.
Edge AI on Constrained Hardware
Applying our SLM findings to constrained, privacy-first environments — voice, routing, and inference on edge devices with limited memory and no network. What works, what doesn't, and where the architecture has to change when cloud isn't an option.
Benchmarks and write-up coming soon.
Private Document Intelligence
On-premise document retrieval combining OCR, vector search, and structured retrieval pipelines. Local SLM handles intent detection and classification — no data leaves the perimeter. Testing how far you can push retrieval quality without cloud AI.
Write-up coming soon.
Working on a similar problem?
We build these so we understand the problems deeply. Let's discuss yours.
Start a conversation