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 19 May 2026
Duration: 00:27:10
Android development is integrating AI and machine learning to merge human-AI workflows, leveraging tools for both manual and automated tasks, reviving command-line interfaces, and balancing intuitive design with technical complexity to enhance productivity and adapt to evolving user needs.
With Google I/O 2026 underway this week, Andrew sits down with Matthew McCullough, VP of Android Development Experiences at Google, to talk about the...
The Android development landscape is evolving to integrate AI and machine learning more deeply into workflows, shifting from traditional UI-focused tools to support both human-driven and AI-agent-driven processes. Developers now have dual-mode access: human-centric workflows for manual, UI-based tasks and agentic workflows that leverage AI for code suggestions, automation, and complex task management. This approach aims to provide seamless, intuitive tools that cater to varying stages of AI adoption, from basic documentation lookups to advanced AI-driven code generation. The industry has rapidly moved from skepticism around AI in development to widespread adoption, with a focus on creating adaptable, scalable, and user-friendly tools that align with the growing complexity of AI-driven applications.
A significant shift in developer roles is emerging, with leading developers moving from coding to orchestrating AI agents, emphasizing strategic planning, product description, and oversight over granular code tasks. This transition highlights a growing demand for skills in product management, strategic thinking, and high-level design. Concurrently, there is a resurgence of command-line interfaces (CLIs) and text-based tools for their efficiency and compatibility with agentic workflows, blending modern practices with foundational techniques. Core principles like rigorous code reviews remain vital for maintainability, while composable tools (e.g., CLIs, APIs) ensure flexibility in complex workflows. Platforms must balance support for both beginners (via intuitive interfaces) and advanced users (CLI/APIs) to sustain innovation and engagement across the developer community.
The focus is on simplifying workflows by removing unnecessary complexity, aligning tools with user needs, and prioritizing empirical validation through open benchmarks. Development practices are shifting from technical minutiae to broader design principles and user-centric goals, with an emphasis on creating "touchable prototypes" over lengthy documentation. Modern IDEs are being adapted for rapid prototyping and integration with existing assets, while collaboration is expanding beyond software engineers to include designers, product managers, and other stakeholders. Natural language is increasingly used as a unifying framework for alignment across teams, and future development must address evolving user expectations for frictionless, anticipatory interactions. Tools and methodologies that democratize software creation are positioning developers and product managers to drive user retention, operational efficiency, and innovation.
What if you integrated AI-agents into your Android development workflow to automate repetitive tasks like code generation and testing?
What if you prioritized CLI-based tools over GUI-heavy IDEs to streamline your development process?
What if you built a composable toolchain using APIs and CLIs to support both beginner and advanced workflows?
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."