Blog
Engineering notes
· From the Lab
Building a Governed AI Routing Pipeline for Regulated Industries
A layered routing architecture that handles PII detection, prompt classification, and model selection across healthcare, finance, telecom, legal, and defence — with deterministic governance at every decision point.
ArchitectureGovernanceSLMPIIProductionEnterprise AI
· From the Lab
Tool Hints vs Model Size: What Actually Makes SLMs Call Tools Correctly
Enum constraints on tool descriptions improved a 1.5B model's accuracy more than upgrading to 7B. Findings from building MCP servers with Ollama.
SLMMCPTool CallingArchitectureEdge AI
· From the Lab
PII Detection Without Cloud AI — Local SLM + Layered Architecture
Most PII detection is pattern matching — deterministic, sub-millisecond, and free. A layered architecture handles 98% without a model. A local SLM covers the remaining 2% without cloud tokens or data leaving your network.
ArchitecturePIIGDPRProductionSLMHealthcareFinanceTelecom