Blog

How I build production LLM pipelines, multi-role B2B platforms and the guardrails around them — written from systems that are actually running. Each post takes one mechanism from a system in production — what broke, why the obvious fix does not work, and the design that replaced it — and links back to the case study it came from.

AI systems2026-07-26

The confidence gate: automate the reading, not the deciding

A confidence gate is the rule set that decides whether a language model's extraction is allowed to reach a customer without a human. Automate the reading — classification and extraction — and keep a person on the deciding. Anything below the gate still gets acknowledged, then queued with the reason it was held.

AI systems2026-07-26

Long-term memory that isn't a chat transcript

Storing conversations is not memory. In a care platform for families raising autistic children, memory is three separate tables — what happened, what is generally true, and what has actually worked — with a scheduled job promoting events into patterns, effectiveness computed as arithmetic rather than model opinion, and every answer citing the family's own record.

AI systems2026-07-26

Natural-language queries without opening your database

Letting recruiters ask questions in plain Turkish means letting a model write SQL against a multi-tenant database. The safety is not in the prompt — it is in a guardrail layer between generation and execution: an allow-listed schema, a forced LIMIT, rejected mutations, and a tenant filter bound as a parameter the model never sees.