Patterns
Architectural decisions we reach for across client engagements.
An LLM is good at reading and bad at being the final authority. A rule engine is the opposite. Four architectures that put deterministic, configuration-driven rules around model output, with a worked example you can audit line by line.
By Amar Mond
There is no single best OCR engine for multilingual documents. The dependable pattern is a router: detect language and script per page and per region, score how hard each page is, send easy pages to a fast conventional engine, and escalate only the hard ones — with verification, because the strongest engines are also the ones that invent text.
By Amar Mond
Setting temperature to 0 does not make a language model repeatable, and for accounting work repeatable is the requirement. The practical answer is to stop asking the model for the final number: let it extract, let ordinary code calculate, validate everything, and record the result so the same document always gets the same answer.
By Amar Mond
Most tasks that get built as agents are workflows, and many workflows are a single well-constructed prompt. A decision framework for picking the simplest architecture that meets the requirement, what each step up costs, and the guardrails an agent needs when you really do need one.
By Amar Mond
Three optimization patterns we apply on most production LLM engagements: semantic routing, custom calibration, prompt compression. Each addresses a different bottleneck. Stacked, they typically deliver 5-10× cost reduction without quality loss.
By Amar Mond
Most production LLM systems track latency and cost. They don't track the things that matter for ongoing operations. Here are the three measurements we insist on before declaring a deployment ready.
By Amar Mond