# CloudThinker Engineering

> The engineering team at CloudThinker writes about how we build software with AI agents. Writing is organized as journeys: one question each, with numbered entries added over time and a "what we think now" summary at the top.

Every journey and entry has a markdown version; the links below point to them. Everything in one file: https://engineering.cloudthinker.io/llms-full.txt

## Journeys

- [Agentic system design](https://engineering.cloudthinker.io/journeys/agentic-system-design.md): How should we structure an agent system so it stays fast, cheap and reliable as tasks get longer and use more tools? (2 entries, ongoing)
- [Generative UI](https://engineering.cloudthinker.io/journeys/generative-ui.md): What should an agent emit when it needs to show someone a dashboard? (1 entries, ongoing)
- [Agentic infrastructure](https://engineering.cloudthinker.io/journeys/agentic-infrastructure.md): What infrastructure do AI agents need to run long, stateful work against private systems, safely and cheaply? (1 entries, ongoing)
- [Agentic memory](https://engineering.cloudthinker.io/journeys/agentic-memory.md): How should an AI agent remember what it learned in past conversations, so it does not start from zero every time? (1 entries, ongoing)

## Optional

- [About](https://engineering.cloudthinker.io/about/)
- [RSS](https://engineering.cloudthinker.io/rss.xml)