Topics

Coding agents are becoming operational workers inside software teams, not just better code completion.

The agent runtime is the system that lets models safely use tools, files, browsers, terminals, and external services.

Agent evals need to measure behavior in a workflow, not only answer quality in a prompt.

Agent memory is not only retrieval; it is a governed write loop that decides what survives a task.

Agent skills package repeatable behavior outside the current chat.

Context engineering is the work of turning scattered organizational knowledge into durable inputs an agent can inspect and act on.