Tag: ai-agents

All the articles with the tag "ai-agents".

• Machines Read, Humans Sign: Code Review in One Year

  Published: October 20, 2026

  13 min read#ai-agents

  What building our own review agent taught us, with our numbers, what Anthropic and one open-source pull request show about where review is going, and eight bets on how teams will review code by October 2027.

• Máquinas Leem, Humanos Assinam: o Code Review Daqui a Um Ano

  Published: 20 de outubro de 2026

  14 min read#ai-agents

  O que construir nosso próprio agente de review nos ensinou, com os nossos números, o que a Anthropic e um pull request open source mostram sobre o futuro do review, e oito apostas de como os times vão revisar código até outubro de 2027.

• Which Keys Is Your Agent Holding?

  Published: October 16, 2026

  3 min read#ai-agents

  A coding agent running in your terminal can use every credential that terminal can reach. heldkeys is an open-source CLI that lists those credentials on your laptop, inside a sandbox or in a CI job, and tells you what to fix first.

• Quais Chaves Estão ao Alcance do Seu Agente?

  Published: 16 de outubro de 2026

  4 min read#ai-agents

  Um agente de código rodando no seu terminal consegue usar qualquer credencial que esse terminal alcança. O heldkeys é uma CLI open source que lista essas credenciais no seu laptop, dentro de um sandbox ou num job de CI, e diz o que resolver primeiro.

• A Capability, Not a Credential: How Our AI Agents Call Customer APIs Without Ever Holding a Key

  Published: October 9, 2026

  8 min read#ai-agents

  Our AI agents write and run code against customers' GitHub, AWS and other systems from a sandbox with internet access, and nothing inside that sandbox can authenticate to any of them. The architecture behind it, the designs we set aside, and where its boundaries are.