Posts
All the articles I've posted.
-
Sovereign AI: Running GPUs On-Prem When the Cloud Isn't an Option
For regulated workloads where the data legally cannot leave a building, on-prem GPU inference is back. The build-vs-rent math, the constraints nobody prices in, and the software that makes a fixed fleet feel like a platform.
-
Small Fine-Tuned Models Are Beating Frontier on My Workloads
On narrow, high-volume tasks a fine-tuned small model matches frontier quality at a fraction of the cost and latency. Here is the pipeline, the eval bar, and the maintenance bill nobody quotes you.
-
Agentic Workflows Need Guardrails, Not Vibes
How to put real constraints around an agent that touches money or production: bounded tools, approval gates on irreversible actions, dry-run modes, spend limits, and a tool-call audit trail you can actually read.
-
Building an MCP Server Fabric for Financial Operations
Instead of one large agent wired to every financial system, a fabric of small MCP servers, each wrapping one system with tightly scoped tools and an approval gate on anything that writes.