Topic
As Coding Agents evolve from code-writing tools to team orchestrators, engineering methods are being redefined. This collection covers frontier practices in Agent engineering: Anthropic's three-Agent architecture, Vercel's design.md methodology, OpenAI's Agent workdays—and how to teach these lessons to your own Agents.
Hermes spent about 15 hours cleaning its own repository while cycling through 1,320 sub-agents. The bigger story is not how much code it deleted, but the shift from coding assistant to autonomous team lead.
Across more than 200 runs, Vercel turned recurring design-review feedback into guidance, shared styles, and deterministic checks so its agents would stop repeating the same mistakes.
Agents are helping researchers run more work in parallel, while pushing human researchers toward judgment, verification, resource allocation, and risk management.