Research Blog
What happens when LLM agents need to remember across sessions — structured memory schemas, retrieval strategies, and the memory-context distinction.
A practical framework for managing prompts as versioned dependencies — tackling drift, regression, and reproducibility.
Why treating prompts as typed, portable artefacts changes how we reason about LLM behaviour — and how promptel implements this idea.
How route-switch uses MIPROv2 to automatically select the right model for each query — balancing cost, quality, and latency.
A post-mortem on building a local LLM serving layer — llama.cpp integration, model management, and where existing tools constrain research.