More The AI Native Dev episodes
Published 10 Feb 2026
Duration: 3398
The shift in software interaction toward AI-native tools enhances user experiences, with emerging observability tools and agents streamlining troubleshooting and making insights more accessible.
"Charts are good for users, not good for agents. Agents look at the underlying data and do deep analysis." Mirko Novakovic built Instana, sold it to I...
The podcast explores how software interaction is evolving toward AI-native, real-time collaborative modes, where users can work with AI agents to enhance tasks like presentation adjustments. A key focus is on the role of OpenTelemetry in standardizing observability data formats, ensuring consistent tagging and cross-vendor integration. This standardization is crucial for improving the quality and usability of telemetry data, which is essential for effective system monitoring and analysis.
The discussion highlights Dash Zero as an AI-native platform built on OpenTelemetry, designed to simplify the onboarding process and offer intuitive workflows for users. Challenges in telemetry data quality, particularly the need for contextual metadata, are addressed, along with how Kubernetes operators are helping improve data consistency across systems. AI agents, such as Root Cause Analysis tools, are being developed to interpret system behavior, analyze logs and metrics, and identify issues using semantic conventions. Although AI still faces limitations in handling large and unstructured telemetry data, there is growing potential for agentic AI to reduce manual effort and empower users with self-service troubleshooting capabilities.
Looking ahead, the future of observability tools is expected to shift toward agent-based systems that emphasize context, user collaboration, and explainability. These systems aim to deliver more actionable insights without requiring deep technical knowledge from end users. The podcast also briefly touches on the convergence of AI, software, and hardware in shaping future career opportunities, pointing to fields like robotics and drones as emerging areas where this integration will play a significant role.
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.