/ ENGINEERING SYSTEMS

FIELD NOTES / ENGINEERING WRITING

Notes from building dependable AI systems.

Field notes on retrieval, bounded agents, evaluation, security, and the production craft behind reliable AI.

READING PATHS

Start with a subject.

FIND IN NOTES
TOPIC
DATE
10 of 10 notes
01
Systems reference

LLM Tool Calling: The Complete Field Reference

A decision-first reference for reliable tool definitions, parallelism, failure handling, provider adapters, argument validation, and multi-turn agent loops.

Tool CallingAgentsReliabilityOpenAIAnthropicGemini
07
Reliability note

Evaluating Faithfulness in RAG Systems

A claim-level evaluation method that separates retrieval defects, generator overreach, judge error, and production release risk.

RAG EvaluationFaithfulnessLLM Reliability
08
Decision note

Release gates for LLM systems

Why quality, security, latency, and rollback evidence should travel together before an AI feature reaches production.

EvaluationOperations