agent architectureAmazon Study Finds One Agent Is the Efficient Default
An Amazon and University of Washington study ran eight agent designs on 13 enterprise SOPs. Coordinated designs used 1.4x to 4.7x the tokens of one agent, and the only significant win came from fixing implementation failures.
November 13, 2026 · 10 min readAgentic AI FoundationCodex and GitHub Copilot Read Anthropic's Agent Skills
AAIF took in Open Responses, Agent Skills, OpenSandbox and OpenEnv at AGNTCon + MCPCon. Two come with tests or validators and named adopters; two are still early.
October 24, 2026 · 11 min readGemini SkillsGoogle ends Gemini Gems for Business and Enterprise in 2027
Google is replacing Gemini Gems with skills. Remaining Gems convert to inactive drafts that only their creators can activate, and Workspace Studio flows with Ask a Gem steps stop working no sooner than March 1, 2027.
October 5, 2026 · 9 min readA2A protocolIBM Wired 6 Agents With A2A. Then Couldn't Upgrade Them.
IBM's TLS platform standardized every agent boundary on A2A and every tool boundary on MCP, which let five of its six specialist agents be built by outside teams. It also left the platform team unable to push a better reasoning pattern into agents it doesn't own — even though every agent already imports the library that contains it.
August 26, 2026 · 14 min readEnterprise AINVIDIA SkillSpector: The $670K Agent Governance Gap, Fixed
NVIDIA shipped Verified Agent Skills and SkillSpector May 22. Trust-tier matrix and 15-point vetting checklist CISOs need before scaling 37 agents.
May 23, 2026 · 16 min read