Latest · AI Engineering
How to Test Go Code That Calls an LLM
Non-determinism does not have to mean untestable. Wrapping the model behind an interface, faking it in unit tests, golden files for prompt assembly, and the small…
4 articles
Claude
Practical Go and web development tutorials: concurrency, performance, backend architecture, testing and DevOps — with runnable code examples.
More articles
AI Engineering
Prompt Caching: The Cheapest Win in Your LLM Bill
Prompt caching is a prefix match, and one stray timestamp can silently disable it. How cache breakpoints, TTLs and the usage fields actually work — and how to build…
AI Engineering
Tool Use in Go: Building an Agent Loop You Can Actually Debug
How LLM tool use really works in Go: the agentic loop, the SDK's tool runner, parallel tool calls, bounded concurrency, returning errors as tool results, and the…
AI Engineering
Calling an LLM from Go: Streaming, Timeouts and the Parts That Bite
A practical guide to wiring Claude into a Go service with the official SDK: content blocks, adaptive thinking, streaming, context deadlines, typed errors and the…