01 / Field notes
Writing from the middle of shipping.
Notes from building AI systems that actually run. n8n agents, Claude Code, MCP servers, retrieval, evals, the parts nobody writes tweets about. 25 posts and counting.
June 2026
Memory · State
AI agent memory, what to persist
Most agent memory systems are a vector store and a hope. Memory is a schema problem first.
9 min read
Alex Cinovoj, TechTide AI
RAG · Retrieval
A RAG pipeline that survives real documents
Your retrieval is not bad. Your PDF parser gave the embedder a wall of ligatures and page furniture.
11 min read
Alex Cinovoj, TechTide AI
May 2026
Cost · Performance
Prompt caching, and the rest of the bill
Most agent bills are 70 percent repeated context. Caching is the cheapest engineering win available.
9 min read
Alex Cinovoj, TechTide AI
Security · Agents
Prompt injection is not a prompt problem
You cannot instruct your way out of injection. You architect your way out of it.
10 min read
Alex Cinovoj, TechTide AI
March 2026
Observability · Ops
AI agent observability, what to log
When an agent misbehaves at 2am, you do not need more logs. You need the right six fields.
9 min read
Alex Cinovoj, TechTide AI
Evals · Quality
LLM evals that actually catch regressions
If your eval suite has never blocked a deploy, it is decoration.
10 min read
Alex Cinovoj, TechTide AI