# Agentic Infrastructure

DevFeed: [Agentic Infrastructure](<https://devfeed.tech/articles/agentic-infrastructure-722.md>)

Original publisher: [Read original article](<https://vercel.com/blog/agentic-infrastructure>)

Author: Tom Occhino

Published: 2026-04-09T07:00:00Z

Content type: article

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [Developer Tools](<https://devfeed.tech/topics/developer-tools.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [llms](<https://devfeed.tech/tags/llms.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

## AI overview

The article argues that coding agents and AI-native software require agentic infrastructure: programmatic, deterministic deployment surfaces that let agents build, test, verify, and ship software autonomously.

## Source excerpt

Every generation of software eventually demands a new generation of infrastructure. First, we configured servers by hand. Next, the cloud turned infrastructure into APIs. Then, a more important shift: infrastructure derived from the application itself. LLMs and coding agents are driving the next transition, and it's happening fast. In the three months leading up to this post's publication, weekly deployments on Vercel doubled, with agents driving the growth. At the time, over 30% of deployments were initiated by coding agents, a 1000% increase from six months earlier. As of September 2026, that share has risen to more than 50%. Software is now agentic Agents are building, testing, and shipping AI-native software, and they're doing it at a velocity that breaks traditional operations. Vercel projects deployed by coding agents are 20 times more likely to call AI inference providers than those deployed by humans. Agents are writing software that uses AI, and agents are building agents. As the final actor shifts from human to machine, infrastructure has to adapt again. It has to work for software that acts on behalf of users, writes itself, and increasingly needs to understand its own behavior in production. This new generation of agentic software demands Agentic Infrastructure. It's not one evolution, but three: Infrastructure for coding agents to deploy to Infrastructure for building and running agents Infrastructure that itself is agentic 1. Infrastructure for coding agents to deploy to The bottleneck for agentic engineering is operational friction. When a coding agent writes a feature, it requires a place to run, test, and verify the output, which ultimately means it needs a URL. If the path from code to running system involves manual Terraform state or clicks in a cloud console UI, the autonomous loop breaks. Agents need programmatic, deterministic deployment surfaces. This is why immutable deployments, preview URLs on every commit, and instant rollbacks aren't just