The agent stack, top to bottom

I've reviewed enough enterprise agent builds to know they fail in the same places, and model quality is rarely why. The usual cause is layer confusion.

Three layers, in order

Tools

Raw capabilities: the model, the APIs, the MCP servers, the vector store. This is the layer where vendors sell you things. It's also the layer that's been commoditizing fastest. Most companies overspend here because it's the part you can shop for.

Skills

Encoded workflows, reusable prompts, tested chains, named playbooks. This is where the company's IP starts to live, in the way it stitches the tools together for its specific work.

Skills are where most enterprise builds get stuck. Engineers want to ship "the agent." But without a skill layer, every agent is a snowflake. Every prompt is a copy-paste. Every fix has to be re-applied across implementations.

Agents

Persistent, role-defined systems that operate in the business. They use skills and invoke tools. They have audit logs, and they have a manager, sometimes human and sometimes another agent.

This is what most companies want when they say "AI strategy." But you can't build an agent layer that works without a skill layer underneath, and you can't build skills without good tools.

What this means in practice

Map the stack you actually have. If you've been buying tools and trying to assemble agents directly, you have a middle-layer problem. If you've got Skills but no agents, you have an orchestration problem. If you've got agents but no Skills, you've built a snowflake that no one will be able to maintain when you leave.

The middle layer is where the work is. The middle layer is also where most of the value is.

(Essay-length take to follow.)