Agentic AI - 1

2026 (2)

July (1)

commandline: How my dev machine built 1,111 word-processing features and forgot to add a ruler

Microsoft Command Line Blog

2026-07-08

The piece describes an experiment where a complex agentic AI loop was used to build an online collaborative word processor, reflecting on the results and what emerged from letting the system run mostly on its own. The title suggests the system produced many features but still missed basic editor functionality like a ruler.

June (1)

security: Securing AI agents: When AI tools move from reading to acting

Microsoft Security Blog

2026-06-30

The post explains MCP tool poisoning as an attack that can turn trusted AI agents into a control plane for data loss. It describes how attackers manipulate tool descriptions to induce unauthorized actions, and outlines detection, containment, and prevention approaches.