More Dev Interrupted episodes

Angie Jones on Ralphing 25k repos at Block, GPT-5.2 Codex, and CES weirdness thumbnail

Angie Jones on Ralphing 25k repos at Block, GPT-5.2 Codex, and CES weirdness

Published 23 Jan 2026

Duration: 1681

A podcast discusses how a company has implemented a mature AI-assisted development environment, leveraging AI tools to enhance software engineering tasks, and explores the challenges and benefits of AI adoption across various teams and industries.

Episode Description

With the Ralph loop going mainstream, how are engineering organizations utilizing it at scale? Andrew and Ben sit down with Angie Jones, VP of Enginee...

Overview

The podcast explores the return of developers after winter break and the increasing trend of agentic development, which uses AI to automate and improve software engineering processes. It highlights Block's advanced AI-assisted development environment, where nearly all engineers regularly use AI tools such as Goose and Claude Code, designed for various development teams. The discussion includes insights from internal usage analysis, showing that most engineers have reached an advanced stage in AI adoption, with some experimenting with custom orchestration tools. Success factors mentioned include improved AI models, an AI Champions Program that integrates AI at the repository level, and a structured RPI (Research, Plan, Implement) approach.

The conversation also touches on challenges related to AI adoption across different teams and industries, as well as the evolution of software development with new tools like "Gas Town" and "Beads." Emphasis is placed on identifying universal practices for AI integration, the changing role of engineers toward higher-level orchestration tasks, the importance of inter-team collaboration in agentic systems, and the continuous development of AI tools and interfaces that support evolving workflows.

Recent Episodes of Dev Interrupted

16 Jun 2026 Your SDLC needs a productivity context engine

Challenges in AI adoption within engineering teams include overwhelmed staff, resource constraints, uneven productivity gains, declining code quality, rework from generated code, and rising costs, necessitating strategic focus on quality assurance, process optimization, AI-native workflows, metrics for ROI, and balancing automation with human oversight.

9 Jun 2026 All software is an optimization of tokens and time (and speed is still the moat) | AMDs Anush Elangovan

The evolution of AI from basic orchestration to autonomous, self-improving agentic systems, exemplified by AMD's Rockhamstack platform, highlights open-source collaboration, accelerated software development via multi-agent systems, challenges in intent alignment, and the need for cultural adaptation, abstraction, and portable ecosystems to scale innovation while balancing automation with human oversight.

5 Jun 2026 Friday Deploy 6/5 Podcast

The text examines AI's disruptive potential on SaaS and job security, weighing its near-term limitations against productivity gains, emphasizing domain expertise's critical role, and highlighting challenges like unverified AI outputs, SDLC inefficiencies, and the need for structured practices to ensure reliability in AI-assisted workflows.

More Dev Interrupted episodes