14 min read
The Microsoft Innovation Podcast: A Nine-Year Wrap
After 836 episodes across seven shows and nearly a decade, I'm wrapping up the Microsoft Innovation Podcast. Here's what the numbers say, what the stats don't capture, and what's next.
Blog
Writing about AI strategy, Microsoft 365 Copilot, and the Intelligence Age.
All (319)Microsoft Power Platform (83)Uncategorised (70)Artificial Intelligence (62)Career Development & Mentoring (60)Microsoft Partners (21)Digital Transformation Innovation (20)Design Thinking & User Experience (2)Podcast (1)
15 min read
I found 268 plaintext secrets in my AI stack
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 what I learned about credentials, AI agents, and the gap between what we build and what we secure.
8 min read
Can I Build This? The Question That Saved Me $10,000 a Year in SaaS Subscriptions
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 building alternatives with AI. Here is what I learned about the subscription economy along the way.
12 min read
44 Safety Rules, 58 Commands, and Microsoft Loop's Missing API - Building Enterprise AI Agent Governance
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 in Microsoft's platform that competitors solved years ago.
6 min read
Connecting AI Agents to Microsoft Planner: ETags, Group Permissions, and the Graph API's Opinions
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 wired 23 AI agents into a real task board.
7 min read
23 Safety Rules I Built Into a Microsoft 365 CLI for AI Agents
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.
10 min read
Shipping a Microsoft 365 CLI: Signed Binaries, SBOMs, and the Bug That Hid for Four Months
Taking cb365 from internal tool to public release meant solving the trust problem: signed binaries, Software Bill of Materials (SBOM), and a certificate authentication bug that only appeared when tested against a real Entra ID tenant.
11 min read
Why I'm Building My Own Microsoft 365 CLI for AI Agents
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 wrestled with, and why security made me almost abandon the whole thing.
11 min read
My AI Agent Now Manages My Microsoft To Do - Here's What Actually Happened
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 why my agent now reviews my task list every morning before I wake up.
8 min read
AI Agents Getting the Date Wrong? Timezone Configuration in OpenCLAW
AI agents have no internal clock. When they run on UTC servers but you're hours ahead, they get dates wrong. Here's a 4-layer fix that works end-to-end.
8 min read
Why I Built My Own Model Routing Engine
How I replaced static model assignments with an autonomous routing engine, shadow testing pipeline, and live dashboard for a 25-agent orchestration platform.
5 min read
Stop searching. Start conversing: how to build real AI skill
Build real AI skill with conversation, not one-shot queries. Use five prompts a day, custom instructions, and voice and vision to improve results.
