17 Nov 2026 Paul Stack: I'll Never Write Infrastructure as Code Again
Agentic infrastructure management and automated alert triage systems reduce operational toil and costs while preserving human judgment for critical decisions.
More The AI Native Dev episodes

Published 17 Feb 2026
Duration: 1877
Agentic development uses AI agents to automate software tasks, shifting the focus to speed and intent-driven specifications while relying on context management to achieve accurate results.
Most teams think agentic dev is about writing better prompts. It's not. Guy Podjarny and Simon Maple explain why managing context, not crafting prompt...
Agentic development represents a shift in software engineering, emphasizing speed and the use of AI agents to automate tasks that are typically done by humans. This approach relies heavily on managing context, which is essential for aligning agents, maintaining institutional knowledge, and ensuring the accuracy of their outputs. Unlike traditional software development, agentic development is non-deterministic, requiring new practices around evaluation, observation, and iterative refinement of context to ensure effectiveness.
A major challenge in agentic development is the tendency of AI agents to re-implement existing code rather than reuse it, along with their potential reliance on outdated knowledge. Managing agent systems in a cost-effective manner is also a key concern. The development process involves continuous cycles of analysis, generation, evaluation, and iteration, with context being updated as systems evolve. Successful implementation depends on effectively communicating context to agents and integrating it into the broader software development lifecycle, much like onboarding and aligning human teams.
17 Nov 2026 Paul Stack: I'll Never Write Infrastructure as Code Again
Agentic infrastructure management and automated alert triage systems reduce operational toil and costs while preserving human judgment for critical decisions.
10 Nov 2026 Edith Harbaugh: Code Is Cheap. The Last Mile Isn't.
Feature flags and AI agents transform software delivery by enabling autonomous rollbacks and rapid iteration, though human judgment remains vital for defining success and maintaining stability.
3 Nov 2026 Maggie Appleton: Agentic Coding Has Outgrown the Text Box
Agentic coding requires shifting from text-based CLI tools to visual, collaborative interfaces to align human planning with agent execution, while humans retain strategic decision-making based on social context.
27 Oct 2026 Caleb Sima: AI Attackers Move at Machine Speed
"AI-driven cybersecurity threats are evolving rapidly, with attackers leveraging speed, complexity, and swarm-like behavior to exploit vulnerabilities, necessitating advanced defensive strategies like automation and high-fidelity monitoring to counter escalating risks."
13 Oct 2026 Maria Gorinova: Feedback Loops That Fix Your Codebase
"Software factories and agentic coding require robust feedback loops to balance efficiency, reliability, and human oversight, with structured workflows and clear intent improving automation outcomes."