We made four websites agent-ready with WebMCP
AI agents already visit our websites and interpret pages built for human eyes. This weekend, we gave all four sites a structured interface they can use safely.

10 articles
AI agents already visit our websites and interpret pages built for human eyes. This weekend, we gave all four sites a structured interface they can use safely.

My AI DevOps board looked frozen for twelve hours. The fix was not smarter orchestration, but a Ralph loop with real hard stops.

Six weeks ago a security audit told me I had 268 plaintext secrets scattered across my AI agent platform. This week I closed out the migration that fixed it. Here is...

A Speechify renewal email made me question every subscription my business pays for. Since January 2026, I have eliminated nearly $10,000 in annual SaaS costs by...

cb365 adds 28 new commands across four workloads with a governance framework inspired by real enterprise AI policy. Three workloads went smoothly. Loop exposed a gap...
Microsoft Planner's API enforces optimistic concurrency with ETags, requires Group membership for plan creation, and uses User IDs for assignments. Here's how I...

How I built 23 hardcoded safety rules into cb365, a Microsoft 365 CLI, to prevent data loss and unauthorised actions when AI agents interact with enterprise systems.
Taking cb365 from internal tool to public release meant solving the trust problem: signed binaries, Software Bill of Materials (SBOM), and a certificate...

Microsoft retired their Graph CLI. PowerShell is the official answer. But AI agents don't speak PowerShell. Here's why I built a new CLI from scratch, the trade-offs...
I designed a Microsoft 365 CLI for AI agents. Then I built it. The Graph API had opinions about my architecture. Here's the build log - the gotchas, the fixes, and...
