AI and Agent Engineering
Production agent systems, measured on completed work.
AI and Agent Engineering · Cloud-Native Engineering
We build AI agent systems that finish the work, and the platforms they run on
Two practices: AI and Agent Engineering, measured on completed tasks, and the Cloud-Native Engineering those systems run on.
The founder’s record
- years in engineering, since 2009
- 17+
- player profiles served at Mobalytics
- 110M+
- global carriers at Nokia Networks
- 15+
Experience behind the work
Mykola Lobanov
Founder & Chief Product and Technology Officer
Co-founder and CTO of Mobalytics from 2016 to 2021. Before that, mobile networks at Nokia Networks from 2009 to 2016.
- TechCrunch Disrupt Startup Battlefield winner, 2016
- CB Insights AI 100, 2018
What we’ve published
4 articles, 11,183 words, on how we build and measure this work.
-
The glyphs we draw our systems with, the rules for putting them together, and the files to draw your own.
- diagrams
- design system
- icons
-
The model benchmark tells you what a model can do. The production benchmark tells you what the system can finish—and at what cost.
- cost per task
- AI economics
- LLM cost
-
From model calls to governed systems that can plan, act, recover, and prove their work
- AI agents
- agent architecture
- MCP