StrongDM Software Factory
StrongDM's field notes on non-interactive agentic development: specs + scenarios, validation harnesses, feedback loops, and the supporting components.
We built a Software Factory : non-interactive development where specs + scenarios drive agents that write code, run harnesses, and converge without human review. The narrative form is included below. If you'd prefer to work from first principles, I offer a few constraints & guidelines that, applied iteratively, will accelerate any team toward the same intuitions, convictions 1 , and ultimately a factory 2 of your own. In kōan or mantra form: Why am I doing this? (implied: the model should be doing this instead) In rule form: Code must not be written by humans Code must not be reviewed by human
saved by
related reading
- How StrongDM’s AI team build serious software without even looking at the codesimonwillison.net
- Notes on the Software Factorybenedict.dev
- Building Effective AI Agents \ Anthropicanthropic.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Building a software factory for AI SDKvercel.com
- dex (@dexhorthy) on Xx.com
- Harness design for long-running application developmentanthropic.com
- Extensible Software in the age of LLMs | Jeremy Morrelljeremymorrell.dev
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- Vibe engineeringsimonwillison.net
- Don’t Outsource Your Thinkingteltam.github.io
- Astra for Coding: Why Are We Doing This Again?lucumr.pocoo.org