The CAFE(S) framework: Improving AI agent effectiveness
As AI agents become more capable, context quality is increasingly the limiting factor in their performance.
Podcast profile
By DX
The show focused on developer productivity and the teams and leaders dedicated to improving it. Each episode features in-depth interviews with Platform and DevEx teams, along with the latest research and approaches for measuring developer productivity.
Latest episode
39 min
Topics
Developer productivity, tooling, workflows, platforms, and engineering enablement.
Managing engineering organizations, teams, delivery, architecture, and technical leadership.
Hiring, career development, skills, workplace practice, and professional progression in technology.
Formats
Detailed technical, architectural, or research-oriented examination.
Host-led conversation where a guest supplies most of the subject matter.
Audience level
Assumes basic technology literacy and familiarity with common products, roles, and terminology.
Stay connected
From the feed
Episodes shown — 10 of 25
As AI agents become more capable, context quality is increasingly the limiting factor in their performance.
Meta researcher Moritz Beller joins Brian Houck to discuss how Meta measures developer productivity. Moritz explains diff authoring time and how Meta uses it to evaluate tools and guide engineering decisions. They explore how AI is changing engineers’ work and revealing gaps in traditional metrics.
In this episode of Engineering Enablement, Robert Lucero, Chief Architect at Okta, joins host Brian Houck to discuss how agentic AI is changing identity and access management.
Max Kanat-Alexander is an Executive Distinguished Engineer at Capital One, where he helps lead developer experience and AI-assisted software development.
AI adoption among software developers is approaching 100%, AI-authored code now makes up more than half of merged code, and developers report saving more time with AI every quarter. But those gains aren’t translating evenly into better outcomes.
Tim Bozarth is a Corporate Vice President in Microsoft CoreAI, where he leads engineering for next-generation developer experiences and Microsoft's Engineering Thrive initiative.
AI coding agents are changing how software gets built, but they're also forcing organizations to rethink how engineering effectiveness is measured. Traditional developer experience metrics were designed for humans, not AI agents, so how should engineering leaders adapt?
Sejal Amin is the Chief Technology Officer at Priceline, where she leads product engineering, infrastructure, data, and technology operations. Pedro Gutierrez is Senior Director of Software Engineering, where he has helped drive developer experience initiatives and the adoption of Priceline's product operating model.
Indeed increased AI coding tool adoption from roughly 25% to 97% across its engineering organization, but getting engineers to use the tools was only part of the challenge.
In this session from DX Annual, Uma Namasivayam, Senior Director of Engineering Productivity at Dropbox, shares how the company's developer productivity efforts evolved from improving developer experience to preparing for the agentic era.