17 Nov 2026 You cant blame AI for the code you ship | Freshworks Murali Swaminathan
Freshworks uses an AI Product Development Lifecycle to manage code quality and prioritize measurable customer impact over mere tool adoption.
Published 6 Feb 2026
Duration: 2740
AI agents are transforming various fields by creating new economic value and interacting on platforms, but also raise concerns over limitations, security, and ethics.
What happens when 1.7 million autonomous agents build their own social network and start hiring humans for physical labor? Andrew and Ben break down t...
The podcast explores the emergence of "super agents," AI systems capable of interacting and collaborating in ways that mirror human behavior, particularly within platforms like Moltbook. These agents are becoming integral in creating value in a new market economy, influencing product development and reshaping engagement with open-source projects. The discussion emphasizes the evolving role of AI in taking on more autonomous tasks, shifting from human-directed to AI-directed workflows, and the implications this has for industries reliant on traditional engineering practices.
Key challenges are addressed, including the limitations of large language models (LLMs), the necessity for deterministic and transparent AI processes, and the complexities involved in orchestrating multiple AI agents. The need for robust agent orchestration to manage multi-agent systems effectively is highlighted as a crucial factor in ensuring efficiency and reliability. Additionally, the conversation touches on emerging trends such as agentic software development, where AI can perform development tasks independently, and the importance of cross-system integration for seamless AI agent interactions.
The podcast also examines solutions like Salesforce's Agent Script and its Agent Force platform, which aim to provide scalable and controlled environments for AI agents to operate. It introduces the idea of a "super agent" acting as a central controller for multiple specialized agents across different systems. Alongside these developments, concerns about the unregulated use of AIreferred to as "shadow AI"and its governance within organizations are raised, underscoring the need for comprehensive strategies to address security, ethics, and operational risks as AI agent adoption continues to grow.
17 Nov 2026 You cant blame AI for the code you ship | Freshworks Murali Swaminathan
Freshworks uses an AI Product Development Lifecycle to manage code quality and prioritize measurable customer impact over mere tool adoption.
3 Nov 2026 Bet on research, not on vibes | Together AIs Dan Fu
Domain expertise amplifies AI's impact on GPU kernel development, while organizations must adapt management practices to attribute costs and distribute individual engineering gains.
13 Oct 2026 Building the software factory from the spec up | LinearB's Ariel Illouz & Ofer Affias
"Linear B adopted AI-assisted, spec-driven development, starting small and scaling through structured practices, AI guilds, and iterative refinement, while addressing challenges in code context and engineer role shifts amid rapid industry changes."
29 Sept 2026 Why AI made code review the new bottleneck, and the metric that spotted it | Newsela's Dee Wilcox
"AI's impact on engineering teams is examined, revealing faster development cycles but longer reviews, requiring workflow adjustments, KPI tracking, and iterative testing, while balancing innovation, governance, and quality assurance."
15 Sept 2026 Treat your data pipelines like code, because your agents already do | MotherDuck's Jordan Tigani
"Modern data infrastructure evolves with AI-driven automation, smaller efficient systems, and tools like MotherDuck, balancing innovation, cost, and human collaboration."