Agentic SDD: Forcing AI Agents to Write Code by Strict Contract
Why canonical SDD turns into dead documentation, and how we built a working Agentic SDD pipeline based on production signals, adversarial model reviews, and BDD checks.
Read →Pavel Volkov · Engineering Notes
Engineering Verifiable Autonomous AI Systems
Field notes on building verifiable autonomous AI systems: executable specifications (Agentic SDD), adversarial multi-model verification gates, and digital employees with shifts, charters, and defined risk boundaries.
Articles
5 essays18 Days Without a Single Task From Me
The first 18 days of an autonomous digital employee on a prediction market: fifty shifts without my involvement, eleven hypotheses, the first profitable month, and two limits it never crosses without the owner.
Read →How I Built a Concierge for Claude Code and Codex
Why dozens of AI sessions force you to delegate not just tasks but their management: a Telegram concierge, a memory of decisions, routing, and result tracking.
Read →How I Built an Autonomous Digital Employee
How my Polymarket trading infrastructure became a proving ground for an autonomous digital employee with a charter, shifts, memory, and SRE on-call duty.
Read →How I Built a Workflow for Autonomous AI Engineering Teams
How I separated roles, checks, and releases so that several AI teams can work in parallel without my constant supervision.
Read →