Blog
Notes on AI engineering
Practical articles on AI agents, RAG, LLM integrations, evals and security — from real projects, no fluff.
Embeddings and chunking for RAG: choosing models, splitting documents and handling Ukrainian text
A practical guide to the retrieval layer of RAG: how embedding models work, how to pick one with MTEB and your own data, multilingual and Ukrainian considerations, chunking strategies, contextual retrieval and reranking.
Vector databases compared: pgvector, Qdrant, Weaviate, Milvus and Pinecone for production RAG
How to choose a vector database: how ANN indexes like HNSW and IVF work, filtering and hybrid search, scaling and costs, and when PostgreSQL with pgvector is all you need.
Multi-agent systems: when several AI agents beat one, and when they just burn tokens
An engineering look at multi-agent LLM systems: orchestrator-subagent architectures, what Anthropic and Cognition learned, why multi-agent systems fail, token economics, and a decision framework for business use cases.
Integrating AI agents with Odoo: JSON-2 API, MCP and safe automation
How to connect an AI assistant to Odoo using the JSON-2 API: API keys, a dedicated integration user, tool design, MCP, and the use cases that pay off first.
Context engineering for AI agents: what to put in the context window and what to leave out
Context engineering explained for developers: why more context hurts, how to budget tokens, just-in-time retrieval, compaction, structured notes, memory and subagents — with patterns for long-running agents.