CEO @Guildai | VP Eng Meta/Instagram | Cofounder/SVP Eng Lightspark | VP Eng Yahoo | CEO Luminate | CTO/Cofounder LiveOps | Netscape Browser Eng Lead, Borland
How you build your agents has a lot to say about how you'll govern them as well.
In his latest, Guild engineer @text2goat will walk you through how he builds an LLM agent on Guild's control plane.
Flexible work has been a passion of mine for a long time. Excited to join the WorkWhile board and help shape how AI can create better outcomes and more opportunity for workers and businesses alike.
Big update from WorkWhile 🚀
We’re thrilled to announce our latest news: “WorkWhile Appoints AI and Infrastructure Leader James Everingham to Board of Directors“.
Get the full story here 👇
#WorkWhile https://t.co/spRRiOaid5
@Microsoft just turned off Claude Code because the usage costs were too high. @ServiceNow blew through their entire 2026 token budget before Memorial Day.
@Uber too.
@Gartner_inc now predicts that over 40% of agentic AI projects will be canceled by the end of 2027, not because the models got worse, but because the economics and the risk profile never closed.
This isn’t a value problem. It’s not even a pricing problem.
It’s a discipline problem.
You can’t control spend until you know how much you’re spending. And you can’t know what you’re spending if you don’t know what agents you’re accountable for in the first place.
- Audit trails.
- Tracked permissions.
- Clear and enforceable ownership standards.
- And the insights to respond quickly when your agents fail.
This is the neutral governance layer that agents have been operating without since GPT 3.
We decided it’s time to build it.
"When I was leading the developer infrastructure team at Meta, we were supporting tens of thousands of engineers, and we started to see the shift—from tools that assist to systems that actually take action... And once that starts to happen, the question changes pretty quickly." - @jevering
→ Ownership.
→ Access controls.
→ Visibility.
→ Cost management.
→ Audit-ability.
When it comes to production agents, the question isn't "does it work?"
The real question is, "who's controlling it?"
Building agents is the easy part.
Managing them safely at enterprise scale isn't.
That's the problem we're solving at Guild.
So, what does that really mean? We'll let James and founding engineer Vincent Durmont tell you in their own words.
https://t.co/NxpwEScN1K
In a world full of surprises, sometimes you just need a little determinism in your life.
In this quick demo, @text2goat will show you how to create deterministic type-script agents with Guild—and satisfy your maniacal need for control.
“Over decades working in infrastructure, I’ve seen this pattern repeat.
A new capability shows up, teams start using it everywhere, and before long they need systems to coordinate and control it… I think agents are heading in the same direction.” -@jevering
Right now the ecosystem is focused on frameworks and SDKs: LangChain, CrewAI, AutoGen, OpenAI’s SDKs, and dozens more.
But once they’re touching source code, production systems, internal tools, customer data, and financial systems, you start needing things like:
- identity and permissions
- auditability and tracing
- operational visibility
- cost and resource control
- safe rollout and rollback
The ecosystem is still focused on building agents.
Eventually it will focus on operating them.
That’s the problem we’re solving at Guild.
Pining for a 3-minute Guild demo? You're in luck.
Check out this quick demo from @text2goat to see how easy it is to get up and managing on Guild's agent control plane. 🛡️ ⚔️
https://t.co/tuTUX2DxE9
Agents Need a Better Control Layer
Anyone can build an agent. But very few understand what they’re doing in production. Or even what they’re allowed to do. That’s an infrastructure problem. And it’s a problem we’re solving here at Guild.
Guild went live with our open beta on Wednesday, and we’re thrilled with the response so far.
So if you have a little time this weekend, I’d love it if you’d give it a try yourself, and if you have any questions along the way, drop me a message, or better yet, share your questions right here in the comments. I’m standing by to answer them!
The team made a short video to explain what we’ve been up to - check it out below.
We’re opening up Guild today.
Agents are already acting in production systems.
Most teams can’t tell you exactly what they did.
That’s a problem.
This requires a control plane.
https://t.co/vCiV7AZMwv
Agents are easy to build.
They’re hard to run.
Then they hit production, and you realize:
— no one knows what they can access
— no one’s tracking what they cost
— no one owns them when they break
Building agents is easy.
Running them is the problem no one’s solved.
We’re hosting Guild Forge in SF on April 29.
Hands-on. No slides. Come build with us.
https://t.co/N3ecqkud4v
Our CEO @jevering on the @ryanlpeterman pod — pre-IPO Netscape, head of eng at Instagram, crypto at Meta, career regrets, and what he's building now with Guild.
Worth the watch ⬇️
https://t.co/l7WzvLWMzh
Getting this in front of our first customers has been 🔥
TL;DR: this is what it looks like when agents stop living inside tools and start operating across your entire engineering system.
Your flash sale is live. Tickets start flooding in.
"Charged but no order." Then another. Then another. 23 customers. Zero fulfillment. Revenue is bleeding and nobody knows why.
A Guild agent picks it up. Searches Jira, queries New Relic, finds the exact buggy line in GitHub.
Root cause, blast radius, recovery plan — delivered to the on-call engineer in 52 seconds.
8 agents. 4 integrations. One control plane.
Speed is killing AI startups.
Not because they're moving too fast, but because they're not building the systems to sustain what they ship.
@jevering breaks down why the next real layer of AI infrastructure isn't another model. It's governance, auditability, and the systems that make agents safe enough to trust inside an enterprise.
Full episode: https://t.co/ulQ54DP36I
Fresh off announcing our Series A, Guild CEO @jevering stopped by @tbpn to talk about the future of AI agents and why enterprises need a control plane to manage them.
When @jevering first described his vision for @GuildAI and how engineering teams will work in the near future, everything seemed obvious in hindsight. Maturing models and agents mean engineering teams will adopt and deploy everything from 3rd-party agents to homegrown systems, each for a specific task. An agent for deployment. Another for code review. Another for product security. This creates the classic enterprise challenge of managing and maintaining all of them.
https://t.co/Ljok5nNwOE is building the control plane for AI reliability, observability, and governance at scale. And there's no better team to do it. They built Devmate @Meta, saw firsthand the viral adoption of this paradigm across a scaled engineering org, and most importantly, lived the challenges after that only show up with scale. And this team learns from their customers fast. I've known @jevering for 6 months and I haven't seen another team in the area that ships and reacts to feedback anywhere near as quickly.
I'm honored to lead @khoslaventures investment in https://t.co/Ljok5nNwOE and to be partnering with James and the team.
Your team runs dozens of AI agents. They run in isolation. No audit trail. No governance. No control plane.
Until now.
Guild is building the Control Plane for AI Agents.
Manage. Monitor. Govern.
https://t.co/i4QbrS9oJG