top of page
AI Architecture


LLM Cost Optimisation: The Cheapest Request Is the One You Never Send
LLM cost optimisation starts before the API call. Learn how caching, deterministic logic, retrieval and precomputation can eliminate unnecessary model requests.
8 min read


AI Architecture: Stop Sending Everything to an LLM
LLMs are powerful, but they should not be the default processing layer for every task. A practical framework for deciding what belongs in code, retrieval, algorithms and AI reasoning.
8 min read
bottom of page
