Insights
RSSField notes from the agent layer
Writing on multi-agent systems, the operational work AI can own, and what we're learning from building and running them.
-
Pilots that never shipped: why successful AI pilots stall before production
Many growth-stage teams have done an AI pilot that worked and somehow never reached production. The reasons are rarely technical. The five patterns we see, and the three pilot-design questions that change the outcome.
-
The EU AI Act is an architecture problem
Most teams treat EU AI Act compliance as a documentation exercise. For agent systems operating in regulated environments, that is the wrong frame. The requirements that matter are built in or bolted on, and the difference shows.
-
Agent systems need custodians, not just builders
Agent systems that work at launch quietly degrade by month six. The named decay modes, the operating discipline that prevents them, and why custodianship is what Tier 04 Manage is actually selling.
-
Implementing a production multi-agent orchestrator: patterns and contracts
A concrete implementation reference for the routing, state, contracts, observability, and recovery patterns that make multi-agent orchestrators hold in production.
-
The orchestration layer is the product
In a multi-agent system, the agents are not the product. The orchestration layer is. What it does, how to architect it, and why the framework choice matters less than taking the layer seriously.
-
Enable before Build: why most teams aren't ready for agent systems yet
Most teams that commission agent systems should have done six months of operator enablement first. Skipping that step is the dominant reason six-figure AI projects underperform. An argument for the unsexy first step.
-
What to automate first: how we rank operational opportunities
Most teams pick the wrong first automation. Here is the ranking framework we use in every Diagnosis: leverage, frequency, tractability, reversibility, and the trap of starting with the loudest pain.
-
How to ship a multi-agent system that survives contact with production
Building multi-agent systems badly is worse than not building them at all. The six disciplines that decide whether yours survives, and the two failure modes you only see in production.
-
Why multi-agent beats single-agent for operational work
Single agents work. Multi-agent systems work differently, and that difference is the whole game for operational functions.