/// BLOG

LOG: BLOG

Ruminations on code, intelligence, and the architectural voids of the modern web.

2026-06-07

How to Write Tests for AI Applications: Test Pyramid, Golden Dataset and CI/CD for LLMs

How to design a test suite for LLM applications: unit tests with mocking, integration tests with a golden dataset, LLM-as-judge evaluation and a quality gate in CI/CD. With real Python code and GitHub Actions.

14 min

Monitoring AI in Production: Metrics, Tracing and Alerts for LLM Applications

2026-06-06

AI & Automation

Monitoring AI in Production: Metrics, Tracing and Alerts for LLM Applications

How to monitor an LLM application so you know about failures before your users do. Three layers of metrics, distributed tracing, automated quality evaluation and alerting systems - with real Python code.

15 min

Structured outputs from AI: Pydantic, Instructor and JSON Schema in production

2026-06-05

AI & Automation

Structured outputs from AI: Pydantic, Instructor and JSON Schema in production

How to stop parsing strings from GPT and start getting data ready to use in code - JSON Schema, Pydantic and the Instructor library.

14 min

AI API Cost Optimization - Caching, Model Matching, Batch Mode and Context Compression

2026-06-05

AI & Automation

AI API Cost Optimization - Caching, Model Matching, Batch Mode and Context Compression

How to cut your OpenAI, Claude and Gemini API bill without losing quality: one call broken down before and after (-68%), caching at three vendors, model matching, batch and Flex modes, history compression and a two-week plan.

11 min

Advanced RAG - Chunking Strategy, Hybrid Search and Reranking in Production

2026-06-04

AI & Automation

Advanced RAG - Chunking Strategy, Hybrid Search and Reranking in Production

Naive RAG with RecursiveCharacterTextSplitter fails on complex documents. How to implement semantic chunking, hybrid search with BM25, RRF fusion and Cross-Encoder reranking - with full production-ready code and RAGAS evaluation.

16 min

Tool Calling in Production - Building Reliable AI Agents with External Functions

2026-06-04

AI & Automation

Tool Calling in Production - Building Reliable AI Agents with External Functions

Tool calling is the mechanism that transforms an LLM from a chatbot into an agent capable of action - calling APIs, querying databases, running code. How to define tools, handle errors, execute in parallel and monitor in production - with full code examples.

14 min

AI Meeting Notes Automation - the End of Manual Minute-Taking

2026-06-02

AI & Automation

AI Meeting Notes Automation - the End of Manual Minute-Taking

The meeting ends, everyone goes back to their tasks - and nobody knows who was supposed to call the client by Friday. AI solves this in 3 minutes: it transcribes the recording, extracts action items with assigned owners and deadlines, and writes them into your CRM and Jira before you close your laptop.

11 min

AI in Content Marketing - A Production Process That Raises Output Without Losing Quality

2026-05-31

AI & Automation

AI in Content Marketing - A Production Process That Raises Output Without Losing Quality

A real agency case where a copywriter went from 24 to about 60 articles a month: how to split work between AI and people, the process step by step, a Make and Notion architecture, pitfalls, a pre-publication quality scorecard and costs.

10 min

TOTAL_RECORDS: 0110

PAGE 11/14

SYSTEM_STABLE