Case Study: Agentic Commerce Can Prove the Payment. It Cannot Explain the PurchaseThe company Call it Harbor, a composite online home goods retailer with a shopping assistant that buys on behalf of customers. A customer types a request, the agent searches several sellers, builds a9 min read·mir-zizka.hashnode.dev1d ago
How to Run an AI Agent Incident Response with ZizkaDB: A Runbook for the First 72 HoursAn AI agent sends the wrong message to a customer. Or it calls a tool it should not have. Or a component it depends on turns out to be compromised. Someone notices, a channel fills with messages, and16 min read·mir-zizka.hashnode.dev2d ago
Why Open Source Still Wins Trust in the AI Era, Even as Attacks Go AutomatedThere is a tempting argument going around. Attackers now use AI to find and exploit weaknesses at machine speed, public code is easy to study, so the safe move is to close the code and hide behind the11 min read·mir-zizka.hashnode.dev2d ago
How to Upgrade Your LLM Without Breaking Production: A Replay Testing Guide with ZizkaDBSooner or later every team running AI agents in production faces the same decision. The model provider is retiring the version you use. A cheaper model has appeared that might do the job. Latency is t14 min read·mir-zizka.hashnode.dev2D4d ago
How to Pass an Enterprise AI Security Review: Build an Evidence Pack That Closes DealsYour demo went well. The buyer's team is excited. Then the deal moves to security review, a questionnaire arrives with dozens of AI-specific questions, and the momentum stops. Weeks pass. Someone asks15 min read·mir-zizka.hashnode.dev5d ago