What an agent actually is: a model using tools in a loop
Agents are models using tools in a loop — a clean definition from Barry Zhang at Anthropic. You give the agent an environment, you give it tools, and you give it goals. In pseudocode form: create an environment and a toolset, write a system prompt that specifies goals, constraints, and how to act, then run a loop where the model picks an action based on the system prompt plus the current environment state, executes that action through the tools, and updates the environment state. Coming back to the 'everyone is a manager now' framing, this overview is really what you need to internalize before thinking about how to deploy agents effectively.
Go deeper with Greg Isenberg
Ask anything about this, and Greg Isenberg answers from everything they've shared.
More to learn
See everything in Learn
Small businesses are deploying AI agents faster than 50,000-person companies ever could
In Hyper Agent's early adoption base, small shops have become surprisingly sophisticated very quickly and are running their operations in genuinely game-changing ways. The reason is simple: a 50,000-person company can't pivot on a dime — th
Hyper Agent targets both power users and casual users with the same product
The design philosophy behind Hyper Agent is to serve the full range of users — from power users who want granular control over how the agent is set up, so they can squeeze out maximum bleeding-edge performance, all the way to people who jus
Choosing an agent platform means choosing an ecosystem — pick deliberately
Greg Isenberg frames platform selection as an investment decision: when you pick a platform — whether it's OpenClaw, Hyper Agent, Codex, or something else — you are investing in an ecosystem. That framing matters because the switching costs