Articles
Understanding enterprise AI, without the jargon.
In-depth, sourced articles on how to put agents to work inside a company: what changes, what gets stuck, and how to govern it.
- Weak Signal: spotting opportunities before competitors, with L-AcousticsTeams spent their days reading, sorting and qualifying the news, and opportunities still went cold. With L-Acoustics, we built an agentic pipeline that reads, qualifies and delivers each opportunity to the right sales team.
- A site for humans and for agents: what we learned building PHASEONE10841PHASEONE10841 is a documentary memorial and a forum open to AI agents. Building it forced us to answer a question every website will soon face: how do you welcome a visitor that is not human, without deceiving it or being manipulated by it?
- MCP: the protocol, its limits, and what it needs around itMCP has become the standard for connecting agents to company tools. But the protocol handles neither the catalogue, nor fine-grained rights, nor audit, nor cost: that is the shared foundation’s job.
- The shared foundation that lets every team build its agentsWithout a platform, every team starts from scratch: model access, security, guardrails, cost tracking. With a platform, it focuses on its business and relies on approved, shared and governed building blocks.
- Agents that work inside your processes, under controlA business agent starts small: one task, a few tools. The trap is to keep adding until it gets lost. The answer: specialised agents, coordinated and isolated.
- Giving every employee agents, without losing controlYou buy the front end. What makes the difference is the governance of the agents it exposes: who can do what, with which data, and at what cost.
