The AI Native Dev - from Copilot today to AI Native Software Development tomorrow

This episode discusses how AI-native development and agentic coding are creating competitive advantages for startups and established companies, highlighting the importance of adopting these practices to avoid falling behind.

This episode explores the evolution of observability in AI-native development, discussing OpenTelemetry standardization, AI agents' impact on software interaction, and career advice for software engineers.

This episode discusses the importance of context management in AI agents and introduces a framework for coordinating multi-agent systems to boost developer productivity.

This episode discusses Phoenix architecture, which advocates for constantly replacing code rather than maintaining it, and explores how AI-generated code can be safely deployed in production.

This episode explores AI engineering practices at major tech companies like Meta, Coinbase, ServiceTitan, and ThoughtWorks, focusing on development processes, productivity gains, and architectural shifts.

This episode announces the launch of TESOL's two products - a spec-driven development framework and spec registry - designed to make AI agents more reliable for developers by using specifications as guardrails.

This episode discusses why top developers prefer IntelliJ and explores the impact of AI tools like Cursor and Copilot on coding productivity.

This episode features an interview with Victor Riparbelli, CEO of Synthesia, discussing AI video technology, its applications in business, and the future of content creation.

The CTO of Snyk discusses AI security concerns, enterprise adoption rates, and developer enthusiasm for AI tools in software development.

This episode discusses how Spring AI serves as a comprehensive framework for AI engineering within Java and Spring ecosystems, enabling developers to integrate AI capabilities through REST calls and microservices.

This episode discusses the concept of skills as reusable context units for AI agents, their lifecycle management, and Tesla's recent implementation of skills support.

This episode discusses how AI-assisted coding introduces hidden security vulnerabilities in software development, featuring insights from René Brandel, co-founder of Casco.

This episode discusses the trust issues and reduced testing in AI-assisted coding workflows, featuring Baruch Sadogursky at an AI conference.

This episode discusses how TESOL's Registry of context tiles improves AI model predictability and abstraction adherence, particularly showing a 50% improvement for new libraries.

This episode explores the challenges and strategies of AI-driven software modernization, particularly focusing on legacy code migration and the practical steps involved in using AI tools effectively.

This episode explores how context is more important than prompts in agentic AI development, discussing its non-deterministic nature, focus on intent over code, and the need for continuous improvement through platforms.

This episode follows a coding challenge where hosts swap town simulator applications built with different AI tools and attempt to add new features live on the show.

This episode explores the future of next-generation AI infrastructure, focusing on voice and video technologies through insights from companies like Datadog, Eleven Labs, and Synthesia.

Alex Gavrilescu discusses BacklogMD, an AI-first project management tool that helps developers create specifications for autonomous AI agents to code tasks.

This episode explores MCP (Model Context Protocol) as a universal plugin system for AI software, discussing its architecture, trust issues, and tools like MCP Run for developers.

This episode explores the evolution of AI agents for developers, focusing on tools like Cloud Code and Cursor, cost reductions enabling recursive agent swarms, and predictions for 2025 as the year of agentics.

This episode demonstrates hands-on prototyping of a SimCity-like town builder using AI-powered development tools like Base44 and Bolt.new for rapid application generation.

This episode explores spec-driven development as a methodology for AI-assisted software creation, featuring a discussion about the Kiro tool and its approach to building software through comprehensive specifications.

This episode explores whether agentic engineering can deliver enterprise-grade code, featuring Reuven Cohen discussing the challenges, the Agentics Foundation's role, and the development of tools like Spark to create repeatable AI-driven coding systems.

This episode explores the differences between memory and context management for AI agents, discussing practical approaches like file systems versus databases and their implications for developers.

David Cramer discusses how Sentry leverages AI and its extensive data to transform debugging and root cause detection for modern software development.

This episode explores AI native development tools like Claude, TypingMind, and MCP servers, focusing on practical applications and extending agent capabilities.

This episode introduces AI agents for developers, explaining their basic components, uses, and differences from other AI types, with a focus on code generation and context management.

This episode discusses how AI is transforming code review processes, featuring Graphite's CEO on integrating AI agents into development workflows without waiting for pull requests.

This episode discusses the development of a Java plugin called DevOps Genie and the growth of Devoxx as a premier Java conference, while positioning the podcast for developers working with AI.

This episode discusses how developers can leverage AI to shift focus from writing code to managing specifications, particularly within the Java and Spring communities, while highlighting upcoming events and insights from previous speakers.

This episode discusses the lasting impact of AI coding agents, exploring productivity gains, spec-driven development, and insights from the AI Engineering World Fair conference with guest Patrick Debois.

This episode discusses how context is more important than model size in AI development, emphasizing that true intelligence differs from mere knowledge and predicting increased use of open models by 2026.

This episode features an interview with Michael Hunger about Neo4j's graph database technology and its applications in modern AI and data management.

This episode explores how Slack's AI agents enhance developer productivity through features like AI explain and product-led development in enterprise settings.

This episode explores the challenges developers face with unreliable AI agents and introduces context engineering as a solution to improve multi-agent system performance.

This episode explores how AI tools like coding agents are transforming software development, focusing on skills that will remain relevant and the transition from GitHub to an AI-focused startup.

This episode explores how AI agents use tools and context to perform tasks beyond just generating text, featuring software engineer Yaniv Aknin discussing his research on enabling top-tier agents.

This episode reveals that 13.4% of AI skills contain critical security vulnerabilities and discusses how attackers could exploit them, while promoting an upcoming AI Native DevCon event.

This episode explores whether AI can build enterprise-grade software through an interview with Maor Shlomo, founder of Base44, discussing their approach to AI-powered app development and its implications for startups.

A Cisco principal engineer discusses CodeGuard, a security solution for AI coding agents that improves baseline performance by 1.79 times.

This episode explores how LLMs can assist with data engineering tasks like data hygiene and testing, while highlighting their limitations with business-specific contexts, featuring insights from Jason Ganz of dbt Labs.

Simon Maple interviews Gal Kleinman, CTO of Traceloop, about LLM observability challenges, focusing on building evaluation suites and monitoring AI applications.

This episode explores how agent experience extends developer experience, emphasizing the importance of supporting AI agents through context files, ephemeral environments, and continuous improvement practices.

This episode features an interview with Ron Eforni, CEO of Phlox, discussing how his company's software infrastructure platform addresses the challenges of deploying AI agents in real-world environments.

This episode explores how organizations can measure and optimize AI usage in software development to drive better results beyond just code generation.

Jonathan Schneider discusses how Moderne's approach to code refactoring shifts from traditional pull requests to more efficient push-based changes that empower developers.

This episode explores how incomplete requirements in AI-driven software development lead to increased rework and introduces the B-MAD (Build More Architect Dream) method as a spec-driven approach to ground models in clear specifications.

This episode explores the transition from traditional software building to orchestrating AI-driven development, featuring guest Annie Vela discussing skills, education, and the impact of AI coding assistance.

This episode features a meetup recording from the London Gen AI community, where Tom Holm interviews Guy Podjarny about AI Native Software Development.

Discussion on open source AI, the value of community, and an upcoming AI Native DevCon conference.

Exploring how AI can generate code beyond simple suggestions, including automating tasks outside the IDE.

An interview with Rishabh Mehrotra from Sourcegraph about AI testing, including context, evaluation, and when to test generated code.

Simon Maple interviews Peter Guagenti about optimizing AI code completion tools for developers.

The hosts and guest discuss categorizing AI development tools to map the AI native software development landscape.