Loop engineering: JobNimbus CAIO demos the daily agent loop system behind Utah's biggest Series B
aakashgupta · x · 2026-09-05
The author frames the industry evolution: prompt engineering (2023), context engineering (2024), harness engineering (2025), and now loop engineering (2026) — echoing OpenClaw founder Peter Steinberger's advice to design loops that prompt your agents for you.
The podcast guest is Tyler Folkman, Chief AI and Product Officer at JobNimbus (Utah's largest Series B ever), who screen-shares the loop system he runs daily. Topics: what makes an agent vs a prompt, writing a skill from scratch live, loops every PM should build, going from 100 ideas to 1 shipped, docs for AI vs docs for humans, and why quality loops beat velocity.
More from coding & agent
- OpenAI publishes GPT-6 Astra model guide with prompting best practices — gabrielchua · 2026-09-05
- OpenAI ships GPT-6 Astra with three new agent-building API updates — gabrielchua · 2026-09-05
- Hamel Husain: Hard-to-eval products are bad products — and AI makes data science more valuable — hugobowne · 2026-09-05
- seq-mcp: An MCP Server Giving AI Agents Controlled Read Access to Seq Logs — modelcontextprotocol · 2026-09-05
- Crew: An MIT-Licensed Desktop App Where Multiple LLM CLIs and People Share One Project — Classic-Grab-2866 · 2026-09-05
- Why agents name folders zz: reverse alphabetical tool ordering surfaces messages first — morqon · 2026-09-05