3 posts tagged with "open-source"

It is easy to create an AI agent. Give a language model a role, connect a few tools, add a goal, and let it run.

It is much harder to create a company of agents.

The moment several agents work on the same outcome, the difficult questions stop being about intelligence. Who owns the task? Which agent has the right context? What may it change? How does work pass from one specialist to another? What happens when they disagree? Where can a human inspect the result and intervene?

These are organisational questions. Answering them requires more than a collection of prompts and chat windows. An AI-agent company needs an operating system.

Intelligence is only one layer​

A reliable internal workflow is more than an efficiency improvement. It can become a capability that customers, partners, and other software systems use directly.

A research workflow can become a market-intelligence service. A document-review process can become an API. A support-triage agent can receive work from external systems.

But publishing a workflow is not the same as exposing an endpoint. The organisational controls that made it trustworthy internally must travel with it.

Building a system for AI-agent companies creates an unavoidable test: can the product help operate its own development?

We have used Flolah's organisational model while shaping Flolah itself—giving work to specialist roles, preserving product knowledge, coordinating through a COO, and keeping consequential decisions with people.

The experience reinforced a lesson that agent demonstrations often miss. Generating work is not the hardest part. Organising responsibility is.