Coding agents and what they cost
3 parts, in reading order
-
Exploring LLMs so our customers don't have to
Norwegian businesses started asking their consultants this in 2026, after a year of quietly running Claude Code. Two decisions hidden in one question, why the endpoint matters more than the tool, what it actually costs, and what March's explore/exploit dilemma says about how a company ends up on one vendor without ever deciding to.
-
Forking Codex to talk to any endpoint
How we restored the Chat Completions wire API in a Codex fork, so one coding agent drives local Ollama models, OpenRouter, Azure OpenAI with Entra auth, or any EU-hosted provider. The three patches that made it usable, the branch model that keeps the rebases to an hour, and why Baldwin & Clark's design rules say the interface was the thing to fight for.
-
Measuring what a coding agent actually costs
A self-hosted OpenTelemetry stack for LLM usage, built as an OpenObserve experiment for customers who keep telemetry on prem: two months of getting the numbers wrong, 118,469 spans of which 118 were useful, and what Rosenberg's learning by using says about why the price list told me nothing.