trending
•

9h ago

What would you trust an AI agent to recommend—but not execute?

Real company processes cross departments, systems, owners, approval boundaries, and different definitions of done.

We encountered this while building automation for our own company, which led us to a more useful question: where should an agent s authority stop?

Think about one recurring process inside your company:

What should an agent be allowed to observe?

•

5h ago

Loopgraph - Open-source loop engineering for autonomous companies

Loopgraph turns recurring company work into governed, visual AI loops. Interview a department, generate versioned LoopSpecs, let Hermes route events to the right loop, then validate, simulate, approve, trace, and review every outcome. Unlike prompt chains and direct webhooks, Loopgraph separates reasoning from authority: Hermes proposes; deterministic policy decides what may run. Open source, local-first, and model-agnostic.