Darek's Blog

A ground-up explainer of the Model Context Protocol: the host-client-server model, the primitives servers and clients expose to each other (tools, resources, prompts, sampling, elicitation), the transports, and the protocol's evolution from the 2024 launch

A field guide to authentication and authorization in the Model Context Protocol: OAuth 2.1 with PKCE, dynamic client registration, client ID metadata documents, machine-to-machine flows, and what changes when an MCP gateway sits in the middle — token pass…

A small prompt habit that changes how a coding agent verifies its own work: stop asking for passing tests, ask it to prove the feature works — once locally against a real Tilt stack with no mocks, then again on staging against real data and integrations.

A follow-up to my LLM cost-optimization post: how I replaced ~55% of the remaining LLM calls in a product classifier with a small local model trained on the LLM's own labels — and why the local model ended up more accurate than the labels it learned from.

A small piece of plastic in our kitchen soap dispenser snapped.

A walkthrough of how I cut an LLM-based product classifier's token usage by ~92% through compression, two-stage prompting, exact-match lookups, similarity caching, and batching.

What the Hell Are Layer2 Rollups?

Hi, I’m Dariusz Dwornikowski Engineering leader with 20+ years of experience scaling tech companies, building products, and leading technical organizations.