More The AI Native Dev episodes
Published 20 Jan 2026
Duration: 1218
The effectiveness of code development is significantly influenced by context, with impact varying from 33% to 80%, and can be improved through the strategic use of coding agents and automation.
Most AI agents fail because you're using them wrong. Heres what actually works in production. In this episode, Simon Maple sits down with Itamar Fried...
The podcast emphasizes the critical role of context in code development, noting that it significantly impacts the effectiveness of coding agents, which can perform anywhere from 33% to 80% effectively. It examines how multi-agent systems can improve productivity and code quality by assigning distinct rolessuch as coding, reviewing, and planningto individual agents, enabling them to work either in parallel or sequentially. Tools like the OpenHands SDK are introduced as platforms for building complex workflows that involve these agents.
The discussion covers various aspects of agent architecture, including the use of diverse vendors to replicate the diversity of human teams and the importance of context management in minimizing errors. It also highlights tasks well-suited for automation, such as dependency management and code upgrades, while underscoring the need for human oversight in areas requiring verification and trust-building. Additionally, the content outlines a structured approach to addressing recurring issues, such as outdated Java versions, through manual investigation, script-based automation, scaling in parallel, and integration with developers.
31 Mar 2026 Why Every Developer needs to know about WebMCP Now
Alternative approaches to Large Language Models are gaining traction, with examples like Apple's offline image detection model and the WebMCPa API addressing AI agent limitations through client-side execution, lightweight local models, and streamlined web interactions while navigating challenges in scalability, cost, and dynamic content.
24 Mar 2026 Stop Maintaining Your Code. Start Replacing It
Phoenix Architecture redefines software development by treating code as disposable, prioritizing enduring system specifications, modularity, AI integration, and balance between automation and human oversight to enable safe, iterative updates and future-ready, adaptable systems.
17 Mar 2026 We Scanned 3,984 Skills 1 in 7 Can Hack Your Machine
AI skills pose significant security risks, with 13.4% containing critical vulnerabilities like prompt injections and unauthorized access, driven by high privileges and obfuscated threats, requiring tools like Sneak/Snyk and complementary measures such as code reviews and supply chain monitoring.
10 Mar 2026 The Greatest Time to Build a Startup (The AI-Native Advantage)
Agentic development uses automated agents powered by Large Language Models to enhance software engineering processes, with benefits including streamlined coding, testing, and collaboration.
3 Mar 2026 Why Your Agent Needs Memory, Not Just Context
Agents contribute to knowledge management by retaining and retrieving information through a combination of embedded models, databases, and large language models.