Urgent.News

What's breaking now, across thousands of outlets.

AI

Presentation: The Reinvention of the Dev Team

Hannah Foxwell shares how the surge of agentic coding forces engineering leaders to rethink team dynamics. She discusses three key anchors for navigating AI-driven velocity: building software worth building, prioritizing automated safety over speed, and preserving the human element through generalist "broken comb" skillsets and sustainable on-call practices. By Hannah Foxwell

Hannah Foxwell, an independent consultant in platform engineering, security, and agentic AI, presents an insightful discussion on the evolution of development teams. She explores the shift from traditional velocity-focused engineering to a new paradigm where AI agents take center stage.

Foxwell argues that while velocity has indeed arrived, organizations are still grappling with how to effectively utilize AI agents in their development processes. She introduces three core principles to guide teams through this transition: building software that holds intrinsic value, emphasizing automated safety over speed, and preserving the human touch through versatile skillsets and sustainable practices.

Foxwell's expertise spans over a decade in platform engineering, and she shares her firsthand experiences of how teams have improved their velocity through incremental advancements in technology. She delves into the transformative impact of Agile, cloud computing, DevOps, and continuous delivery, showcasing how these innovations have accelerated software development.

The introduction of AI agents, such as those utilized in platforms like Cursor, represents a significant leap forward. These agents are now capable of performing a multitude of tasks, from writing tests to deploying applications, thereby reshaping the roles of human developers. Foxwell emphasizes that the future of software development will likely involve a collaborative effort between humans and AI agents, each contributing their unique strengths to the process.

Her talk serves as a cautionary yet optimistic exploration of this emerging landscape. While she acknowledges that many organizations are not yet prepared for the implications of AI-driven development, she encourages experimentation and learning from the experiences of early adopters. Foxwell believes that by grounding their vision in the three anchors outlined, teams can navigate this new era of software development with confidence and foresight.

Written by urgent.news from InfoQ's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at infoq.com →

More in AI

ButterflyBench: I Changed One Instruction. What Else Did the AI Change?

This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked One of my test prompts said: "Read JSON files instead of CSV." In more than half of my reruns, three models answered by…

  • ButterflyBench measures AI model changes with small instructions
  • Author tests 40 scenarios on 20-setting command-line tool
  • Some models struggle with undoing earliest changes

More from Wednesday 7 October →