Podcast
43 articles tagged The AI Native Dev - from Copilot today to AI Native Software Development tomorrow.
An analysis of how agentic coding shifts software development from individual execution to collaborative planning. This brief explores the limitations of text-based interfaces, the role of visual boundary objects, and the strategic redefinition of PM and engineering roles in an AI-native workflow.
AI-driven attackers operate at machine speed, rendering traditional human-led defense obsolete. Enterprises must shift to autonomous remediation, high-fidelity detection, and deception-based containment to survive the new threat landscape.
A strategic framework for securing autonomous AI agents in software factories. Learn how to implement sandboxing, least privilege, and supply chain controls to mitigate risks from probabilistic AI actors.
Enterprise adoption of agentic AI is accelerating but faces a critical security gap. This analysis explores the shift from co-pilot to autonomous agents, the rise of the 'autonomous attacker,' and the strategic necessity of automating security remediation to manage technical debt.
This analysis explores the architecture of agentic software factories, focusing on the implementation of inner, middle, and outer feedback loops. It details how engineering teams can transition from manual prompting to autonomous, self-healing systems by treating code, context, and data as integral factory components.
Legora CTO Jacob Lauritsen details how AI writes 100% of their codebase and drives $200M ARR. Learn about agentic orchestration, the verifier rule, and why human judgment remains critical in high-stakes legal decisions.
An analysis of how engineering teams can scale AI-assisted development without sacrificing reliability. Key insights focus on the critical role of human ownership, the shift from code creation to review bottlenecks, and the necessity of robust observability and CI/CD foundations to support agentic workflows.
An executive analysis of the shift from manual coding to agentic software factories. This brief examines the critical need for human oversight in AI-generated code, the risks of architectural drift, and the strategic value of codifying engineering taste into reusable skills and context.
Mark Brooker of AWS discusses the future of agentic software development, emphasizing the shift from code writing to specification building. Key insights include the critical role of deterministic policy languages like Dogwood, the automation of on-call tasks, and the strategic value of agent memory for organizational learning.
An analysis of the shift from junior coding to agent orchestration, the distinction between deterministic workflows and true agentic systems, and the adoption of law-firm-style revenue sharing in software agencies.
TESOL demonstrates how shifting from manual coding to agentic loops increases PR volume by 850 per week while improving quality. This analysis details the strategic transition from skills to autonomous factories, emphasizing context-centric governance and verifiable standards for enterprise scalability.
Principal Engineer Lada Kessler shares advanced strategies for agentic coding, including the 'centrifuge' refinement loop, skill-based activation, and deterministic verification. Learn how to manage AI complexity, enforce honest output, and build trusted software factory building blocks.
GitHub researchers describe continuous AI as a new layer beside CI/CD for repository-centered automation. The discussion covers guardrails, cost control, human review, and practical patterns for agentic workflows. It positions the repository as a production site where teams can run AI agents with bounded authority. The takeaway is that AI value is shifting from individual chat tools to operational systems that improve software continuously.
This episode examines how agentic systems force a redesign of identity, authentication, and authorization. It explains why non deterministic behavior is both a capability and a security risk. The discussion covers mission based permissions, hard boundaries, and emerging protocols for agent identity. It also outlines the market opportunity for tools that make autonomous agents safe to deploy at enterprise scale.
The Datadog AI developer experience program shows how agentic coding scales from tool adoption to governed workflow. The company used evals, context hygiene, and team ownership to reduce risk in code review and model selection. The result is a practical framework for engineering leaders who need measurable, cost-aware AI development.
TESOL reports that 65 to 70 percent of pull requests now flow through an autonomous dark factory. The system uses Linear tickets, sandboxed coding agents, CI checks, and layered verification to ship code with minimal human review. The model shifts engineer work from writing code to defining scope, context, and quality guardrails. This creates a scalable operating model for AI native software teams.
The discussion examines how reusable agent skills create a new software supply chain and why prompt injection is a critical enterprise risk. Snyk and Tessal are integrating automated skill scanning, versioning, and security scores into registries to support safe adoption. The analysis outlines governance controls for internal skills, credential management, and agent behavior guardrails. These practices help CISOs approve agentic coding rollouts without sacrificing developer productivity.
Sierra built an internal agent platform that combines whitelisted tools, citation based output, and a knowledge graph. The system supports operations, support, and product workflows while limiting data leakage risk. The case study offers a practical framework for scaling AI agents in regulated environments.
An executive analysis of the shift from individual AI coding to organizational agentic platforms. This brief explores how continuous learning, shared context, and feedback loops create competitive moats, while addressing cost management and the evolving roles of engineering teams in the AI era.
Anthropic's Claude Tag shifts agentic coding from single-player IDEs to multiplayer Slack environments. This analysis covers the 65% PR automation metric, the 'Dreaming' memory feature, and the strategic shift toward asynchronous, trust-based development workflows.
An executive analysis of the shift from interactive AI coding to autonomous loop engineering. Learn how to build composable software factories, optimize agent costs, and leverage verifiers to scale agentic workflows without sacrificing control.
Expert panel discussion on enterprise AI enablement, focusing on the shift from human-centric to agent-centric software delivery. Key insights include the necessity of deterministic CI/CD harnesses, the 'Plan-Merge-Polish' workflow, and the critical role of observability in agentic coding. Learn how to balance speed with quality and manage token costs effectively.
Analysis of AI Native DevCon 2026 highlights, focusing on the strategic shift from vanity metrics to business outcomes. Covers harness engineering, agentic workflow bottlenecks, and the critical role of change management in scaling AI adoption across enterprise teams.
Industry leaders from Cisco, GitHub, and Netlify discuss the critical security gaps in agentic AI adoption. The analysis covers prompt injection risks, the shift to agent-ready web architectures, and the strategic imperative for developers to embrace AI-native workflows to avoid obsolescence.
OpenAI engineer Ryan Lopopolo details the shift from pair programming to autonomous agent orchestration. Learn how harness engineering, zero-human-review workflows, and spec-driven development are redefining software velocity and quality control in the AI era.
Jellyfish data reveals a 2x increase in merged pull requests but highlights the 'agentic barrier' of human attention limits. Engineering leaders must shift from output metrics to business outcomes to satisfy CFO scrutiny in 2026.
A strategic analysis of the shift from code-centric to agent-centric security. Key insights on managing non-deterministic AI behavior, the security implications of agent skills, and the necessity of agentic security frameworks for enterprise adoption.
Agentic AI introduces novel security vectors, including prompt injection and context supply chain attacks. This analysis outlines the 'Lethal Trifecta' of agent vulnerabilities and provides a framework for implementing least-privilege controls, context manifests, and human-in-the-loop governance to mitigate risk in AI-native engineering teams.
Venkat Subramaniam argues that AI is an accelerated inference engine, not true intelligence. This analysis explores the critical need for human discipline, critical thinking, and risk management to mitigate the legal and reputational consequences of AI-generated code in production environments.
Rod Johnson argues against the Python-centric AI narrative, advocating for Java-based enterprise AI integration. He details the Embabel framework's use of deterministic GOAP planning to ensure explainability and control in agentic workflows, challenging the 'vibe coding' approach.
Industry leaders from Stripe, OpenAI, and Google DeepMind discuss the obsolescence of traditional CI/CD in the age of AI agents. Key insights cover harness engineering, context optimization, and the strategic shift toward specialized open models for enterprise deployment.
Logan Kilpatrick from Google DeepMind discusses the shift from prompt engineering to context engineering, the rise of agentic coding, and why AGI will emerge as a product ecosystem rather than a single model. Key insights on developer productivity and future software roles.
This executive brief analyzes the shift from spec-centric to context-centric development in the AI era. It highlights the obsolescence of manual code review, the rise of agent onboarding, and the strategic imperative for enterprises to automate the entire software development lifecycle to maintain competitive speed.
