It’s been about a month since I published the LightningCopilot guide, integrating Microsoft Copilot Studio Agents into Salesforce Lightning with Entra ID SSO and MSAL.

What’s interesting is how many teams I've talked to saying they hit the same blockers!

The hardest part of the LightningCopilot project wasn’t building the LWC.
It was getting Entra ID, Power Platform, and Copilot Studio to all agree on who you are — silently.

Federated credentials, custom scopes, Static Resources instead of CDNs… a dozen small things that had to line up!

AI agents are moving from buzzword to baseline.

Most companies plan to make them core to their AI strategy within a year.
Want to learn how to build one the right way?

Check out the Microsoft Copilot & AI Agents Summit (Nov 26–27).
Real examples, and practical frameworks!

#MS-FTE #Microsoft

Finally published the LightningCopilot walkthrough, how to run a Microsoft Copilot Studio agent inside Salesforce Lightning with Entra ID SSO + MSAL.
It’s a proper step-by-step, not another “just drop an iframe” post.

Remember: agents drift when they reread their mistakes. Trim history, externalize state, feed less back. Reliability rises.
#ThursdayThoughts #AI #LLM #AIAgents

Majority voting barely improves long-horizon reliability. Thinking tokens, ie: "reasoning" before acting, win every time. Pay for the right compute.
#ThursdayThoughts #AI #LLM #AIAgents

My desk looks like a small tornado passed through, coffee mug, cables, notebooks, and a few rogue spinner magnets that didn’t survive another fidget session.
Some people need calm to focus; I apparently need creative chaos.
Curious, what’s the one item on your desk you can’t live without?

Agent build tip: Plan externally, execute in small, verifiable steps. Cleaner pipelines.
#ThursdayThoughts #AI #LLM #AIAgents

Entra rollout made easier.
Check out these step-by-step deployment videos for Microsoft Entra, covering hybrid join, Conditional Access, and more. Perfect for IT admins in the trenches.

Ghost citations, part 2: my 7-step checklist to keep AI-assisted content faithful, accurate, and complete. Move fast—without burning trust.
Link in first reply.

Drift happens when agents read their own bad outputs. Cut context, watch error rate, escalate sooner. Human in the loop!
#ThursdayThoughts #AI #LLM #AIAgents

Step 1: Create the PIM‑enabled group.
Entra → Group → Enable PIM → add Eligible Member assignments (time‑boxed).
Full guide (pics): aka.ms/defpim
#EntraID #PIM #LeastPrivilege

An “ethical AI” report shipped with 15+ fake citations. Why? Hallucinations + humans pasting smart-sounding lines. I share a simple playbook to stop ghost citations and keep trust.
Link in first reply.

💭 Track horizon length, not just accuracy. Tiny per‑step gains can mean big jumps in how far agents run without help.
#ThursdayThoughts #AI #LLM #AIAgents

Still giving standing access in Defender XDR?
Use PIM‑for‑Groups + URBAC for JIT, time‑boxed permissions.
Clean guide from Matt Novitsch → aka.ms/defpim

Air-gapped networks aren’t as secure as many think. Stuxnet proved that. Insider threats prove that. Meanwhile, HTTPS/TLS provides a controlled, encrypted tunnel—similar to a VPN. It’s time to rethink our approach to security.

Read more in my latest blog post: buff.ly/4hDd9dU
#CyberSecurity #VPN

Went live with @Merrill last week to break down the new Conditional Access deployment guide + setup.cloud.microsoft. Super slick way to deploy CA right. 🔐

Catch the replay here: www.linkedin.com/events/entra...
#EntraID #Microsoft365 #Security

VPNs are widely trusted for security, but HTTPS/TLS achieves many of the same security goals—just at the application layer. If we trust VPNs, why dismiss HTTPS/TLS as “open internet”?

I break down the misconceptions in my latest post: buff.ly/4hDd9dU

<a href="/hashtag/CyberSecurity" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link">#CyberSecurity #ThreatIntel #Encryption

No data center? No problem.
I built an AI chatbot with Docker, an RTX 3080, and NGINX—secure, fast, and fully local.
Check it out: https://buff.ly/40WeBlT
#AI #SelfHosted #LLM #Docker #NGINX

Huh what - local inference with docker? Yup.
✅ Local inference with vLLM
✅ Secured with NGINX & Certbot
✅ Fast, private, and free
Here’s how: https://buff.ly/42CUF8N
#AI #SelfHosted #Docker #LLM #APIFree