Daniel Worku was supporting a team of 3,000 engineers at Netflix when he realized something was broken. Despite building Netflix Console—the most-used internal tool that helped ship major features like ads, live streaming, and games in record time—engineers were still spending 20-30% of their time on tedious tasks outside their code editor. Bug fixes, deployments, performance issues, and production incidents consumed hours that could be spent building.
"We had this amazing tool for tracking services and pinging engineers, but it had no AI," Worku recalls. "It was basically a manager's bookkeeping tool. The last project my team worked on was called Change Automation, but it was pre-AI—we were hand-coding templates."
That's when Worku reconnected with his longtime friend Yonas Beshawred, who had just sold his developer tools company StackShare to FOSSA. The two had met at a Bay Area hacker house a decade earlier, bonding over a shared love of Ethiopian culture at a party. Their friendship had grown over the years—Beshawred was even a groomsman at Worku's wedding in 2021.
"When we talked about building an internal developer portal for engineers with AI, Yonas was like, 'I'm down to do it again,'" says Worku, who had always planned to return to startups after stints at Facebook and Netflix.
Now part of Y Combinator's S25 batch, the StarSling team turned to Mastra in early 2025 to build their vision: an AI-powered system that brings the magic of Cursor to all the engineering work that happens outside the code editor.
Yonas Beshawred and Daniel Worku, co-founders of StarSling.
The Vision: Cursor for Everything Outside the IDE
StarSling's mission is to revolutionize the 20-30% of engineering work that happens outside the code editor. While tools like Cursor have transformed how engineers write code, Worku describes stepping outside the IDE as "walking back to the stone age."
"Let's say I'm done writing in the code editor. I need to deploy to production, optimize a slow database query, or debug an exception," Worku explains. "That unplanned work—those annoying alerts that pop up—that's what we're building for."
The team is starting with a focused approach: a prioritized inbox that integrates GitHub, Linear, and Sentry. When an exception appears, engineers can click an "Autofix" button that launches an AI agent to debug the issue, find the root cause, and open a pull request—all without leaving their homepage.
StarSling's Autofix feature in action.
Screenshot: StarSling's Autofix feature in action
Why Mastra Powers StarSling's Agent System
As StarSling began building their AI-powered DevOps assistant, they faced a critical architectural decision. They needed to create multiple specialized agents—each handling different aspects of the engineering workflow—while maintaining seamless integration across various developer tools.
"We evaluated LangGraph and considered building something custom," says Worku. "But Mastra's modular agent framework and workflow engine were perfectly suited for what we needed."
Here's how StarSling architected their solution with Mastra:
Frontend: Like Vetnio, StarSling uses assistant-ui, a responsive frontend with deep Mastra integration that works seamlessly on desktop and mobile.
Agent Orchestration: Mastra's workflow orchestrator intelligently routes tasks to specialized agents based on the type of engineering work—whether it's fixing a Sentry exception, updating a Linear task, or opening a GitHub PR.
Cross-Tool Integration: The real power comes from Mastra enabling agents to work across multiple developer tools. "The autofix feature requires getting data from Sentry, opening a GitHub PR, and potentially linking to a Linear task," Worku explains. "Mastra makes this orchestration seamless."
Infrastructure: Following their commitment to modern, scalable architecture, StarSling runs on serverless infrastructure using Vercel and Cloudflare. They're also big believers in open source—alongside Mastra, they use Better Auth for authentication and Inngest for data syncing.
Looking ahead
The StarSling team found Mastra's comprehensive documentation and responsive Slack support crucial for their rapid development. "If you have questions, beyond getting a fast response from Abhi or Shane, you can look at the code yourself," notes Worku. "Open source is a huge unlock."
This ease of integration let the team focus on their core mission instead of building infrastructure. While they're launching with the autofix feature, their vision extends to a comprehensive system of agents for all developer tasks outside the IDE. The team is rapidly growing; StarSling is looking to hire their first engineers.
"Every engineer who has code in production does this type of work," Worku emphasizes. "Especially when you're on-call, this 20-30% of your time becomes 60-70%. We're building Cursor for DevOps—bringing that same AI-powered experience to everything that happens after the code is written."