Building with AI as the team.
Strategy, product, engineering, finance, marketing — one founder, AI as the team. Field notes from running JourneyBay, Kronos, and a one-person stack.
Flagship launches
What I’m building
Two products that show how I run AI as the team.
Kronos Agent OS: a self-hosted runtime for durable AI agents
An evidence-based tour of KAOS v0.3.0: durable turns, layered memory, MCP tools, governance, behavior evals, portable agent state, and safe defaults.
JourneyBay 2.0: An AI Travel Engine That Holds the Entire Trip in One Itinerary
JourneyBay 2.0 is live - an AI Travel Engine that edits your trip instead of just answering questions. A trip from one prompt, booking import from PDFs and photos, visa context from official sources, bring your own LLM key, and MCP access for Claude Desktop, Codex, and Cursor.
Featured reading
Where to start
Three pieces that capture how I think about AI-augmented building.
Context Engineering for LLM Agents: A Practical Guide
Build reliable context for LLM agents: select evidence, separate instructions from data, manage tools and memory, compact safely, and test what the model receives.
Claude Code Guide: Setup, CLAUDE.md, Skills, MCP, CI
AI coding for Flutter: a verification-first workflow
Latest
Fresh from the workbench.
AI Agent Memory: Sessions, Long-Term State, and Retrieval
Tutorials AI OpsDesign AI agent memory without a data swamp: session state, durable facts, retrieval, provenance, conflicts, privacy, deletion, and production evaluation.
MCP Security: OAuth, Tool Permissions, and Prompt Injection
Tutorials AI OpsSecure remote and local MCP servers with OAuth audience binding, least-privilege tools, prompt injection defenses, sandboxing, audit logs, and tests.
How to Test an MCP Server: Contracts, Failures, and CI
Tutorials EngineeringTest MCP servers beyond the Inspector: schemas, protocol versions, auth, timeouts, cancellation, retries, failure injection, conformance, and agent behavior.
Production LLM Stack: Routing, Evals, Cost, Reliability
Tutorials AI OpsA practical production LLM stack: request contracts, model routing, tools, validation, observability, evals, cost controls, fallbacks, and safe rollouts.
AI Lead Scoring: A Validation-First B2B Guide
Tutorials SalesBuild AI lead scoring that ranks B2B leads with evidence, holdout metrics, human review, and safe CRM writes—without treating scores as probabilities.
Product Demo Run Sheet: Show One Buyer Workflow
Tutorials SalesPrepare a buyer-specific product demo from verified discovery notes, rehearse the environment, handle failures, and record a concrete next step.
By topic
Four pillars I write about most.
Engineering
Software engineering practices, architecture, testing
- How to Test an MCP Server: Contracts, Failures, and CI
- Terraform Modules with AI: IaC for Startups Without a DevOps Engineer
- Docker Multi-Stage Builds: Smaller, Safer Images
Product
Product management, research, specs, prioritization
- Finding Edge Cases in PRDs with Claude: 23 Missed Scenarios in One Prompt
- Usability Test Script with AI: A Step-by-Step Guide
- Design System Prompt Library: Getting Consistent UI from AI
AI Ops
Running AI systems in production
- AI Agent Memory: Sessions, Long-Term State, and Retrieval
- MCP Security: OAuth, Tool Permissions, and Prompt Injection
- Production LLM Stack: Routing, Evals, Cost, Reliability
Strategy
Business models, market sizing, competitive analysis
- Living CI Document: Competitive Intelligence That Updates Itself
- Competitive Intelligence Report in 30 Minutes: Prompts and Template
- Feature Matrix Template: AI Turns Screenshots into Competitive Insights
About the author
Roman Belov — technical founder. 10+ years in product (Yandex, OZON, VK), now full-time on AI-augmented building. Writes weekly about engineering, product, and operations with AI as the team.
More about me →