Tag: AI Agents
3 postsModel Ergonomics: How Harnesses Shape Agent Capability
The same model can behave very differently under a different harness. This article examines model ergonomics: the fit between models, tools, context, feedback, and execution environments, using Grok on the Codex harness to explore the boundary between generalized and specialized harnesses.
SeriesRuntime Architecture of LLM Agents1/2Architecture
From Tool Calls to an Event-Driven Runtime: The Runtime Architecture of LLM Agents
LLM agents should not be understood as a chain of tool calls; as tasks grow longer and environments become more complex, the runtime needs an event-driven architecture for state, concurrency, observation, and recovery.
SeriesRuntime Architecture of LLM Agents2/2Control Flow
Who Calls Whom: Understanding LLM Agents Through CSP and Coroutines
Instead of understanding LLM agents as models calling tools, we can view them as systems made up of communicating processes and coroutines; this perspective better explains event sources, control transfer, suspension, and recovery.