Articles tagged with "Architecture"
How We Built a 30-Action AI Agent Platform in 6 Months
The complete architecture of a production AI agent platform: intent classification, graph-based routing, multi-model consensus, and an approval queue. Real numbers from 6 months in production.
Ostap Kovalisko
Founder & AI Systems Architect
The Approval Queue Pattern: Human-in-the-Loop for AI Agents
Why fully autonomous AI agents fail in enterprise settings, and how the approval queue pattern — AI proposes, human decides — makes AI adoption possible. Design guide with risk tiers and UI requirements.
Ostap Kovalisko
Founder & AI Systems Architect
Real-Time AI Chat: WebSockets vs Polling in Production
We shipped a production AI chat on 5-second SWR polling before touching WebSockets. When polling is the right call, when it stops being enough, and how to migrate.
Ostap Kovalisko
Founder & AI Systems Architect
LLM Cost Optimization: Small Models for Routing, Big Models for Judgment
Production LLM bills are an architecture problem, not a pricing problem. The tiering, caching, and routing strategies that cut our per-query cost by 90%.
Ostap Kovalisko
Founder & AI Systems Architect
Building Agents with the Claude API: Routing, Vision, and Tool Use
How we use the Claude model family in production agents: Haiku for sub-200ms routing, Sonnet and Opus for judgment, vision for documents, and tool use for actions.
Ostap Kovalisko
Founder & AI Systems Architect
Building Your Own Jarvis: Personal AI Assistant Architecture in 2026
What it actually takes to build a Jarvis-style personal AI assistant in 2026: the four layers, the integrations that matter, and the mistakes that kill v1.
Ostap Kovalisko
Founder & AI Systems Architect
Tool Use and Function Calling: How AI Agents Touch Real Systems
Function calling is easy to demo and hard to productionize. How we design tool layers for AI agents across 9 connected systems: schemas, idempotency, permissions.
Ostap Kovalisko
Founder & AI Systems Architect
Graph Routing vs Prompt Chains: Building Deterministic AI Agents
Prompt chains are easy to start and impossible to debug. Graph-based routing makes agent behavior deterministic, testable, and safe to change. A comparison.
Ostap Kovalisko
Founder & AI Systems Architect
Intent Classification with LLMs: Sub-200ms Routing for AI Agents
How to route user requests to the right AI action in under 200ms using embeddings, confidence tiers, and a small classifier — without burning a full LLM call.
Ostap Kovalisko
Founder & AI Systems Architect