Today we’re launching Managed Deep Agents - the easiest way to build, run and deploy production agents. We have a full release blog and docs if you want to read more. In this article I want to talk about the journey to get here and why I’m so excited about what I think is the next step of agent building.
I think there are a few distinct periods of agent building.
Briefly covering two of the earlier ones:
Early AI Frameworks/Apps (Late 2022/Early 2023): LangChain was launched October 2022, ChatGPT in November 2022, AutoGPT early 2023. All of these were early AI frameworks or apps that first started to leverage LLMs.
More mature AI frameworks like LangGraph, Google ADK, Vercel’s AI SDK emerged in 2024 and first half of 2025. These gave developers more control over LLMs. People we’re really building agents we think of them today, but they were able to build more complex AI apps.
Sometime in early to mid 2025 the models started to get good enough to power what we think of agents today: LLMs running in a loop calling tools. This is the core primitive, the core algorithm, that underpins agents today. Really early agent apps like Manus, Deep Research, and Claude Code followed this same pattern.
When the models became good enough to just run in a loop and call tools, this became a more solid foundation we could build upon. The concept of Agent Harnesses like Claude Code, Pi, and Deep Agents emerged as we figured out the rights tools and environments to add into this loop. We launched Deep Agents nearly a year ago - one of the first attempts to take some of the patterns we saw in the application layer and bring them to a general use harness.
Over the past year, there have been two set of learnings that have shaped the next direction.
First, we started to learn some of the common primitives for running these agent harnesses at scale. Things like durable execution to back the running of the agent loop, and sandboxes for running untrusted code. “Separating the brain and hands” became a common design choice. The infrastructure required for running these agents started to become more known.
Second, standards for how users should drive these agent harnesses emerged. Things like AGENTS.md for base set of instructions, MCP for plugging into other systems, skills for progressive disclosure of context. These became standards to control and drive parts of harnesses.
Both of these contributed to the rise of “managed agent” experiences. Where the agent harness is run on managed infrastructure, and builders use these standards to drive agent behavior.