The AI discourse right now is dominated by visions I do not believe will come to pass in the next decade. Download a business, import it, run it. Agents that replace entire departments. The permanent underclass of displaced knowledge workers.
I think this is wrong. AI infrastructure will work the same way every other infrastructure wave has worked: with a ton of low-level primitives that slowly get built up into something useful. The companies that try to skip straight to the grand vision will burn through capital and credibility. The companies that start small — one workflow, done well, for a specific team — will compound their way into something much larger.
The path is not glamorous. It is not a demo that makes a VC gasp. It is a developer who was annoyed by a repetitive task, built a workflow agent to handle it in a weekend, and then never thought about that task again. Multiply that by every developer in the organization, and you have something that looks a lot like an agent mesh — not because someone architected it from the top down, but because it grew organically from the bottom up.
If you are leading an engineering or AI team and trying to figure out your agent strategy, here is what I would suggest. Stop trying to hire an agent for a role. Identify the three most annoying, repetitive workflows your team does every week. Build agents for those. Make them good. Make them inspectable. Let your developers own them. Then do three more. Then three more after that.
You will end up with something far more valuable than a role-based agent that kind of works at everything. You will have a portfolio of workflow agents that each work extremely well at one thing, that your team actually trusts, and that compound in value every week they run. The gap between AI demo and AI deployment is not a model problem. It is a software engineering problem — and software engineering has always been about building small things well and composing them.
Related Essays
Follow No Goose Absolutely
Design partner programs prevent enterprise AI companies from building three products when they should have built one.
From Agent to Platform: Why the GTM Is Services-Shaped
There is no winner-take-all platform in agents. The GTM is services-shaped, the harness is commoditized, and coding-agent companies have a narrow window to pivot before the floor falls out.
Three Audiences, Three Agent Strategies
Executives, founders, engineering leaders. Each one needs a different mindset shift to operationalize agents in 2026 — and each one is currently running the wrong play.
Key takeaways
- AI infrastructure builds the same way every other infrastructure wave has — low-level primitives composed into something larger.
- The path is not glamorous; it is one developer building a workflow agent over a weekend, then never thinking about that task again.
- The portfolio of scoped agents your team trusts will outperform a role-based agent that kind of works at everything.
FAQ
What is the practical starting move for an engineering leader?
Stop trying to hire an agent for a role. Identify the three most annoying, repetitive workflows your team does every week. Build agents for those. Make them inspectable. Let your developers own them. Then do three more.
How does an agent mesh actually emerge?
Not by top-down architecture. By accumulation. A developer is annoyed by a repetitive task, builds a workflow agent in a weekend, and never thinks about it again. Multiply that by every developer in the org and you have a mesh that grew bottom-up.