Engineering Blog

Inside the machine

Deep dives into the engineering decisions behind KaryoSpace, written by the person who made them, for the people who want to understand why.

What building observability into a production AI product taught me about LLM failure modes
Most AI products are black boxes twice over. The model is a black box to the developer, and the product is a black box to the user. AIO changed that, and what it surfaced was not what I expected.
Read article
Why I built my guardrails before the model, not after
The standard advice is to filter LLM outputs. I filter inputs instead, intercepting before the model is ever invoked. Here's the design, the reasoning, and what the adversarial tests revealed.
Read article
Building a RAG pipeline without frameworks: what I learned
No LangChain. No LlamaIndex. No abstraction layer. Just Go, MongoDB, and a pipeline I understand completely. This is what the decision cost me, and what it taught me.
Read article
Coming soon
AI Systems
KRE: building a knowledge refinement engine that actually surfaces gaps
Infrastructure
Writing an SMTP + IMAP server from scratch in Go: the decisions I regret and the ones I don't
AI Safety
Multi-LLM routing in production: when local inference is good enough and when it isn't
Contact Us
Message sent!
We read every submission and will get back to you.