Engineering
Engineering
Practical notes on AI systems, distributed computing, and production engineering.
Automating Medical Coding Final Part
Once a medical coding pipeline maps a clinical concept to an ICD-10-CM code, it is tempting to declare victory and celebrate but story does not end here given…
7 min read
Automating Medical Coding Part 1
To a novice engineer healthcare coding looks simple from the outside. A clinician writes a discharge summary. Medical Coder reads it. A set of ICD-10-CM codes…
5 min read
Automating Medical Coding Part 2
There is a particularly dangerous phase in building an LLM system. It produces an answer. The answer looks correct. You celebrate. Then you try 100 examples…
3 min read
Beating The Black Terminal
For local AI development, the ritual usually involves installing Python, Docker, an inference server, a vector database, several model files, twelve libraries…
7 min read
Building First LLM
All Experiments with Large Language models begin with chat windows You type a question, the model produces an answer, and yada yada. This serves the purpose,…
7 min read
Building LLM Router
Most LLM applications begin with an llm call response = client.chat.completions.create( model="premium-model", messages=messages, ) This is a reasonable…
7 min read
Deterministic Testing The LLMs
The first version of an LLM application usually has a test that looks suspiciously like this: response = openai.chat.completions.create(...) assert "refund" in…
5 min read
Semantic Cache To LLM Rescue
(Repo url) LLM applications have an unusual relationship with repetition. Users repeatedly ask: How do I reset my password? Then they ask: I forgot my…
8 min read
Testing LLM Workflows Locally
(Repo and examples can be found here) Knowing that an LLM should be mocked is the easy part. The harder question is how to mock it without creating a cardboard…
7 min read