Roee Adler
@roee
Co-Founder and CEO at @hud_hq. Formerly Envara (aq by Intel), AeroScout (aq by Stanley), Soluto (aq by Asurion), Santa & WeWork’s OG CPO. Also 👩🔬👧👧👦🥋🤓⚽️
This is huge for production applications! Literally every developer has to deal with server errors they can't reproduce, and it doesn't matter how many logs they have. You don't have to be "every developer" anymore. Look into Hud's Runtime Code Sensor. Hud is one of my…
A major challenge for AI code generation is shipping code that actually works in complex real-life environments. On June 25th we’re teaming up with @awscloud to show how Q Developer + @hud_hq deliver production-safe code. Seats limited - sign up here: aws-experience.com/emea/smb/e/edf…
What started as a coincidence (many team members wearing the same light purple Uniqlo shirt on a Thursday) became tradition and homage (on Thursdays we wear purple, #meangirlsforever), and like everything in startup lore - ended up becoming swag 💜 @hud_hq

AWS just announced the new marketplace for AI Agents, and we are proud to be a launch partner! If you’re on @awscloud it’s now much easier to get @hud_hq - just search "fix production issues".. We’re honored to be in the first group included, alongside titans like @AnthropicAI
Great vibes at EuroPython today! 🔥 It was really exciting to discuss the future of monitoring in the era of #AI and showcase some of what we've built at @hud_hq for self-healing production with coding agents like @github Copilot and @AnthropicAI 's Claude CLI, utilizing @ThePSF…
To reason, plan & fix in complex real-world systems, AI coding agents need more than just the code. They also need ubiquitous, function-level production context. Hud (@hud_hq) captures exactly that, with zero configuration. Now agents know how code actually behaves 🤩
🚨 @github just dropped their new AI coding agent for Pro & Enterprise users Naturally, I threw it straight into production to fix my real bugs. 😈🐞 It worked!! Here’s what happened 👇🧵
I swear the best part about Gemini CLI is the texts while we wait. I almost want the agent to take more time. Nice one @googledevs @GeminiApp! ✨
We all love a nice HTTP 500 error in production. Would you trust an AI coding agent to just fix it? Will it have all the right context to succeed? Well, with @hud_hq it will. Try it out at hud.io 😎
🚨 Most devs ship code without really knowing how it behaves in production. Meet Hud, the first Runtime Code Sensor built for humans and AI agents. Here’s how it changes everything 👇 🧵
Agentic code generation is a one way street. Models & agents will get better, but - code alone can never be sufficient context for this future, to be able to generate code that actually works in complex production scenarios. That’s where @hud_hq comes in -->
In this great paper the researchers showed how runtime context must “speak the language” of the code- with functions and code lines, to be able to connect to coding agents. Just think about what we can achieve if this was production context from reality using @hud_hq 🤩
LLMs Don’t Think Like Developers - Until Now. Together with @KatzShachar and @liorwolf We made LLMs execute their code while generating it, just like a human developer. Meet EG-CFG: A new inference-time method that injects real-time execution feedback into the generation loop.…
Say hello to @hud_hq's new Fix It flow 🤩 Now when an endpoint throws an error in production, information about it is automatically packaged with function-level root cause data, allowing your favorite AI IDE/agent to just fix it. No configuration needed! Check it out -->
Nice graph 🤩 These are weekly hud-sdk downloads for @nodejs - if you're using AI code generation to build on Node - give it a try! Source: npmjs.com/package/hud-sdk
AI development is moving fast, but real world complexities slow it down. We built @hud_hq to fix that. From the runtime up. Here I share how our lightweight Runtime Code Sensor, installed a minute with zero configuration, starts to unlock something new...
AI code gen is at a massive inflection point. But- there’s a difference between generating code in green-field environments vs in complex production realities. We believe the necessity for production-aware development is here. Read @hud_hq's story --> hud.io/introducing-hud
Had a great time speaking at @geektime main stage about building MCP servers from our experience @hud_hq. While it's hard to say if MCP will be *the* future protocol, it was a powerful unlock and it's worth understanding why its KISS approach won so many hearts at @MCP_Community
If you are in Amsterdam on June 20th, come hear our co-founder and CTO @maywa1ter’s keynote at DevOpsDays about the similarities between medical emergency rooms and dealing with production incidents 🤩 talks.devopsdays.org/devopsdays-ams…