Caring is the moat, you should feel visceral pain when things are bad or broken and stop at nothing to fix them

@byron_miller the uknowable is one thing, the unimaginable is another. @snowded spoke about this some in his @devopsdaysATL keynote earlier this year

youtu.be/7Ng5P42OKmA

When anyone can build anything, how do you make something people actually choose?

At AGNTCon I talked about why building something great is only half the job.

My favorite part is always the conversations afterward. Grateful I got to share the stage with @techgirl1908 and things I talked about is public signal. What people actually understand and remember about your product.

We have so much content now, but how much of it actually helps people understand what we’re building?

AI summarizes and remixes your content, leaves out important details, or exaggerates small things until customers start hearing promises you never made.

And somehow, genuinely different products end up sounding exactly the same.

So if your product isn’t converting, maybe you don’t need more content or better distribution. Maybe you need to understand what people are actually hearing about your product, and whether that’s what you intended.

This is one of my favorite problems to help teams solve, so let’s chat!

If you’re at AGNTCon + MCPCon, come check out my talk, “Authorization After OAuth: Controlling Tools on Hosted MCP Servers You Don’t Own” at 3:30pm!

Room: 230A (Concourse Level)

events.linuxfoundation.org/agntcon-mcpcon…

Security is a process. We are working the process of security.

As we ask how “we” adapt to this more dangerous cyber-context, I bet we’re thinking mostly w/in incredibly well resourced orgs…

Want to get hands-on at AGNTCon+MCPCon?
Come to our workshop combining Ollama, Pydantic-AI, FastMCP, Redis, Docker, OpenTel, Grafana, and Kubernetes.
IRL @ 10:55 AM, or try it at home here:
github.com/bbenz/stack-it…

When AI agents can build anything, how do you decide what's actually worth building?

Lena Hall, Senior Director of Developers and AI at @Akamai, took the AGNTCon + MCPCon NA keynote stage with “The Anything Trap: What to Build When Agents Can Build Everything.”

Because the hard ents can build. It's knowing what they should build. Join the livestream: bit.ly/3U6tMrS

@sarah_edo, Distinguished Engineer at @Google, just took the AGNTCon + MCPCon NA keynote stage to talk about “The Agentic Web.”

What happens when AI agents become part of how we navigate and interact with the web? This is the conversation you don't want to miss. bit.ly/3U6tMrS

We're donating Agent Skills to the Agentic AI Foundation (@AgenticAIFdn), the same foundation we donated MCP to.

Since December 2025, 70+ agent platforms have integrated the standard, including ChatGPT, Cursor, GitHub Copilot, and VS Code.

Here's what that means for you:

We got @lenadroid keynoting at AGNTCon + MCPCon.

The Anything Trap: What to Build When Agents Can Build Everything

'This is absolutely not being overhyped'
I spoke to @sherrod_im at @PaloAltoNtwks @Unit42_Intel about the PHP flaws and AI's cybersecurity reckoning
The Palo Alto Networks’ Unit 42 threat intelligence chief says AI-driven vulnerability discovery is “the new normal” — and explains why she’s surprisingly optimistic.
groundlevel-ai.com/p/php-vulnerab…

Sooo excited to welcome four new projects to the Agentic AI Foundation! 🎉

- Agent Skills
- Open Responses
- OpenEnv
- OpenSandbox

Huge thank you and congrats to Anthropic, OpenAI, Hugging Face, and Alibaba for contributing these projects to a neutral home ❤️

Truly honored to of each.

@nickytonline @KateHolterhoff @techgirl1908 @devopsdaysATL a deeper take is how #mcp & #webMCP more specifically fit into this ecosystem. I think there's an opportunity to more clearly negotiate boundaries & expectations with agents than just hard blocking them.

@nickytonline @KateHolterhoff @techgirl1908 I flew out here to research our #dataSecOps topic for @devopsdaysATL

TL;DR
I've been using agentic coding practices in non-prod to build hardened web applications for years now.

Can we run agents in prod safely?
is it worth the $ or the headache?
can we afford not to? 🤔

Things that aren’t security controls:

- thoughts and prayers
- alignment
- prompts prohibiting action
- saying “not my circus not my monkeys”
- “it is what it is”

Feel free to add 😂

What did people think “focus on security” meant? It meant this. It meant finding all these problems (of which there are so many more) and fixing them.

The goal isn’t to have an easy day at the office. It’s to make sure people don’t die. It’s to stop truly horrible cyber attacks.

@sherrod_im @ABCNewsLive submit your talk today 👇
talks.devopsdays.org/devopsdays-atl…

did you see @sherrod_im on @ABCNewsLive w/ insights & updates on #php2shell ?

Will there be a more significant security incident between now & her keynote at #devopsdays #Atlanta in April? 🤔😅
🔒🐢🦀🦑🤫

Our CFP is open!
super early bird tix will be available soon!

Me, thinking PHP had been largely deprecated, looking around the internets this morning: