I Gave Claude Code Our Entire Codebase. Our Customers Noticed. | Al Chen (Galileo)
Al Chen, a field engineer at observability platform Galileo, used Claude Code to index the company’s 15 Git repositories and merge that context with Confluence and Slack data. He built a 16‑line script that continuously pulls the latest main branches, enabling real‑time, hyper‑personalized answers to customer deployment questions. The system replaces static documentation, dramatically lowering engineering interruptions and turning one‑off queries into reusable knowledge. By automating code‑base queries, Galileo delivers a support experience that scales with enterprise demand.
An AI State of the Union: We’ve Passed the Inflection Point, Dark Factories Are Coming, and Automation Timelines | Simon...
Simon Willison, a veteran Django co‑creator, argues that November 2025 marked a decisive inflection point when AI coding agents moved from experimental to reliably productive. He describes how he now writes 95% of his code from a phone, leaving him mentally...
Genie Sessions: TCR Skill
In this live, unscripted "Genie Session," the host experiments with building a Cursor skill that enforces a Test‑Commit‑Revert (TCR) workflow while developing a left‑leaning red‑black tree in Python. The discussion covers the history of software development playbooks, the challenges of...
Cilium, eBPF, and Modern Kubernetes Networking with Bill Mulligan
In this episode, Bill Mulligan, a maintainer of Cilium and member of Isovalent, explains how eBPF—a safe, programmable extension to the Linux kernel—revolutionizes networking for cloud‑native environments. He details Cilium’s role as a Kubernetes CNI that leverages eBPF to provide...
How Stripe Built “Minions”—AI Coding Agents that Ship 1,300 PRs Weekly From Slack Reactions | Steve Kaliski (Stripe Engineer)
Stripe’s internal AI coding agents, dubbed “minions,” now produce roughly 1,300 pull requests each week with only human code‑review oversight. Engineers trigger the agents from Slack reactions, which then spin up cloud‑based development environments to write, test, and submit code...
New: OAuth for MCP Servers — Lessons From Building for AI Agents
In this episode, the Semaphore team walks through the implementation of OAuth for their MCP server, detailing the challenges of client registration, dynamic discovery endpoints, and evolving MCP specifications. Amir shares practical lessons learned from testing across multiple agents, handling...
Semaphore’s New Pricing Model: Built for the AI Era of CICD
In this episode, Pete Milorovic announces Semaphore's new pricing model tailored for the AI-driven, always‑on CI/CD era. The plan separates compute costs from support and success services, lowers per‑minute rates for high‑performance F1 machines to $0.0075, and shifts self‑agent billing...
#540: Modern Python Monorepo with Uv and Prek
In this episode, host Michael Kennedy talks with Apache Airflow core contributors Yarek Patuk and Amag Desai about how they manage one of the world’s largest Python monorepos—over a million lines of code and 100+ sub‑packages—using modern tooling like UV,...
From Figma to Claude Code and Back | Gui Seiz & Alex Kern (Figma)
In this episode Claire Vo talks with Alex Gee, an engineer, and Guy Seiz, a designer at Figma, about new AI‑driven workflows that let design and code move back and forth seamlessly. They demonstrate how the Figma MCP (Multi‑modal Code‑to‑Design...
Anthropic Launches "Code Review" To Fix AI Code Security Issues
In this episode, host Jaden Schaefer discusses Anthropic's new "Code Review" tool, which automatically analyzes AI‑generated pull requests to flag logical errors and security risks before they reach production. He explains how the flood of AI‑written code has created a...
Product News: OAuth Authentication for the Semaphore MCP Server
In this episode, Pete Milorovic announces an upcoming update to the Semaphore MCP server that adds OAuth authentication, replacing the current reliance on long-lived API tokens. The new flow lets developers authorize agents via a browser, simplifying credential management and...
AI-Assisted Coding Needs More than Vibes; It Needs Containers and Sandboxes
In this episode, Docker President Mark Cavett discusses how containers are becoming essential for safely running AI‑generated code, emphasizing the need for hardened images to bridge the trust gap. He explains Docker’s new open‑source Docker Hardened Images (DHI) catalog, which...
Product Update: AI-Driven Onboarding and Workflow Automation in Semaphore
In this episode, Pete outlines Semaphore's new AI-driven assistant that streamlines CI/CD onboarding by converting natural language descriptions into fully configured pipelines. The assistant also offers ongoing workflow insights, error explanations, reruns, and configuration suggestions while preserving full developer control...
Killing Clusters & Orchestrating Chaos with Colt McNealy | Ep. 20
In this episode Tim Berglund talks with Colt McNealy, founder and CEO of Little Horse, about building a Kafka‑based platform for orchestrating microservice workflows and AI agents. Colt describes how his early experience debugging monolithic code with GDB contrasted with...
Talking Drupal #540 – Acquia Source
In this episode the hosts dive into Acquia Source, the fully managed Drupal SaaS platform, exploring its evolution, pricing, and how it enables organizations to scale and customize Drupal experiences. Guest Matthew Grasmick explains the technical challenges of building a...