AI Safety
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.
July 2025
12 min read
Suman Akkisetty
Read article
AI Security
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.
July 2025
10 min read
Suman Akkisetty
Read article
ML Systems
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.
June 2025
11 min read
Suman Akkisetty
Read article