New course: Building Coding Agents with Tool Execution, taught by Tereza Tizkova and Fra Zuppichini from E2B. Most AI agents are limited to predefined function calls. This short course teaches you to build agents that write and execute code to accomplish tasks, accessing entire programming language ecosystems instead of being restricted to a fixed set of tools. You'll learn to run agent-generated code safely in sandboxed cloud environments that protect your systems from harmful operations. Skills you'll gain: - Build agents that write and execute code, manage files, and handle errors autonomously through feedback loops - Run agent code safely in E2B cloud sandboxes and understand tradeoffs between local, containerized, and cloud execution - Create a data analyst agent that explores visualizes data with Pandas - Create a full-stack agent that builds complete Next.js web applications Join and build agents that code their way through complex tasks: https://lnkd.in/gmbUriZf
It was an honor to work with you 🫶
By enabling agents to write and execute code rather than rely on predefined functions, developers gain access to exponentially more possibilities. The emphasis on sandboxed execution addresses critical security concerns while maintaining flexibility- particularly valuable is the practical focus on real-world applications like data analysis and full-stack development.👏
I have been using E2B with KodeAgent for a while, and it has been a great experience.
The course focuses on practical skills for building agents that generate and run code securely. You learn how to manage sandboxed execution, handle errors, and supervise feedback loops. It shows how these agents can perform data analysis or assemble complete web applications. The outcome is a clear method for extending what AI can do in real workflows.
Love seeing the shift from simple function-call agents to ones that can actually write and run code — this is the kind of capability that will make AI genuinely useful for real-world workflows.
I love how this course quietly announces the end of “prompting” as we know it. This is the moment where Satya Nadella’s old line becomes real: software that writes software. Most companies still think AI agents are glorified chatbots. Meanwhile E2B is teaching people to build agents that spin up full Next.js apps while your team is still arguing about coding guidelines. From my seat as a CIO, this is the part nobody wants to hear. If agents can write, run, debug and iterate their own code, the entire delivery model shifts. Not in 2030. On a random Tuesday. Strong course. Massively underestimated. Anyone ignoring this will soon be outpaced by their own agents.
Really enjoyed working in this! 🫶
LOL , what is Ana de Armas doing in deeplearning.ai ? i thought it was a sci-fi movie ads 😁
Very useful for local workflows. Come share what you build and learn with 9,000+ of us in the AI Agents group on linkedin: https://www.linkedin.com/groups/6672014
Love this! Most “AI agents” are still basically on training wheels, so teaching them to write and run real code feels like the upgrade they desperately needed.